Reproducibility Index

Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

International Conference on Machine Learning (ICML) - 2020

Documentation Rate of Empirical Papers by Reproducibility Variable

Distribution of Empirical Papers by Number of Documented Variables

Website:

Venue	Year	Papers	Reproducibility Score Reproducibility Score based on Gundersen et al. (2025). See Methods for details.	Documentation Score Documentation Score is the average score over the seven reproducibility variables for empirical research papers. See Methods for details.	% Empirical Percentage of papers that are empirical research vs theoretical research.	% Industry Percentage of empirical research papers with at least one author from Industry.	Website
ICML	2020	1084	0.52	3.43	90.68%	44.05%

Search Papers

	Pseudocode	Open Source Code	Open Datasets	Dataset Splits	Hardware Specification	Software Dependencies	Experiment Setup
(Locally) Differentially Private Combinatorial Semi-Bandits	✅	❌	❌	❌	❌	❌	❌	1
A Chance-Constrained Generative Framework for Sequence Optimization	✅	❌	✅	✅	❌	❌	✅	4
A Distributional Framework For Data Valuation	✅	✅	✅	❌	❌	❌	❌	3
A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation	✅	❌	❌	❌	❌	❌	❌	1
A Flexible Framework for Nonparametric Graphical Modeling that Accommodates Machine Learning	❌	❌	❌	❌	❌	❌	❌	0
A Flexible Latent Space Model for Multilayer Networks	✅	❌	✅	❌	❌	❌	✅	3
A Free-Energy Principle for Representation Learning	❌	❌	✅	❌	❌	❌	✅	2
A Game Theoretic Framework for Model Based Reinforcement Learning	✅	❌	❌	❌	❌	❌	❌	1
A Generative Model for Molecular Distance Geometry	❌	✅	✅	✅	✅	❌	❌	4
A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton	❌	❌	✅	✅	✅	❌	✅	4
A Geometric Approach to Archetypal Analysis via Sparse Projections	✅	❌	✅	❌	✅	❌	✅	4
A Graph to Graphs Framework for Retrosynthesis Prediction	❌	❌	✅	✅	✅	❌	✅	4
A Markov Decision Process Model for Socio-Economic Systems Impacted by Climate Change	✅	❌	✅	❌	❌	❌	✅	3
A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth	✅	❌	✅	❌	❌	❌	✅	3
A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits	✅	✅	✅	❌	❌	❌	❌	3
A Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block Model	✅	❌	❌	❌	✅	✅	✅	4
A Pairwise Fair and Community-preserving Approach to k-Center Clustering	✅	✅	✅	❌	❌	❌	✅	4
A Quantile-based Approach for Hyperparameter Transfer Learning	✅	❌	✅	✅	✅	❌	✅	5
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning	❌	❌	❌	❌	❌	❌	❌	0
A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition	✅	❌	✅	✅	❌	❌	✅	4
A Simple Framework for Contrastive Learning of Visual Representations	✅	✅	✅	✅	✅	❌	✅	6
A Swiss Army Knife for Minimax Optimal Transport	✅	✅	✅	❌	❌	❌	✅	4
A Tree-Structured Decoder for Image-to-Markup Generation	❌	❌	✅	✅	✅	❌	✅	4
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates	✅	❌	❌	❌	❌	❌	✅	2
A distributional view on multi-objective policy optimization	✅	✅	❌	❌	❌	✅	✅	4
A general recurrent state space framework for modeling neural dynamics during decision-making	❌	✅	✅	✅	❌	❌	✅	4
A new regret analysis for Adam-type algorithms	✅	❌	❌	❌	❌	❌	❌	1
A simpler approach to accelerated optimization: iterative averaging meets optimism	✅	❌	❌	❌	❌	❌	❌	1
ACFlow: Flow Models for Arbitrary Conditional Likelihoods	❌	✅	✅	❌	❌	❌	❌	2
AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation	❌	❌	✅	❌	❌	❌	❌	1
Abstraction Mechanisms Predict Generalization in Deep Neural Networks	❌	✅	✅	❌	❌	❌	❌	2
Accelerated Message Passing for Entropy-Regularized MAP Inference	✅	❌	❌	❌	❌	❌	✅	2
Accelerated Stochastic Gradient-free and Projection-free Methods	✅	✅	✅	❌	✅	❌	✅	5
Accelerating Large-Scale Inference with Anisotropic Vector Quantization	❌	✅	✅	❌	✅	❌	✅	4
Accelerating the diffusion-based ensemble sampling by non-reversible dynamics	❌	❌	✅	❌	❌	❌	✅	2
Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization	✅	❌	✅	❌	❌	❌	✅	3
Acceleration through spectral density estimation	✅	❌	✅	❌	❌	❌	❌	2
Accountable Off-Policy Evaluation With Kernel Bellman Statistics	✅	❌	✅	❌	❌	❌	✅	3
Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generation	❌	❌	✅	✅	❌	❌	✅	3
Active World Model Learning with Progress Curiosity	✅	❌	❌	❌	❌	❌	✅	2
AdaScale SGD: A User-Friendly Algorithm for Distributed Training	✅	❌	✅	✅	❌	❌	✅	4
Adaptive Adversarial Multi-task Representation Learning	✅	✅	✅	✅	❌	❌	✅	5
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE	✅	✅	✅	❌	✅	❌	✅	5
Adaptive Droplet Routing in Digital Microfluidic Biochips Using Deep Reinforcement Learning	❌	✅	❌	❌	❌	❌	✅	2
Adaptive Estimator Selection for Off-Policy Evaluation	❌	✅	✅	❌	❌	❌	✅	3
Adaptive Gradient Descent without Descent	✅	✅	✅	❌	❌	❌	✅	4
Adaptive Region-Based Active Learning	✅	❌	✅	✅	❌	❌	✅	4
Adaptive Reward-Poisoning Attacks against Reinforcement Learning	✅	❌	❌	❌	❌	❌	✅	2
Adaptive Sampling for Estimating Probability Distributions	✅	❌	❌	❌	❌	❌	✅	2
Adaptive Sketching for Fast and Convergent Canonical Polyadic Decomposition	✅	✅	✅	❌	❌	❌	✅	4
Adding seemingly uninformative labels helps in low data regimes	❌	✅	✅	✅	❌	❌	✅	4
Adversarial Attacks on Copyright Detection Systems	❌	❌	❌	❌	❌	❌	❌	0
Adversarial Attacks on Probabilistic Autoregressive Forecasting Models	❌	✅	✅	✅	✅	❌	✅	5
Adversarial Filters of Dataset Biases	✅	✅	✅	✅	❌	❌	✅	5
Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks	❌	❌	❌	❌	❌	❌	❌	0
Adversarial Mutual Information for Text Generation	❌	✅	✅	✅	❌	❌	✅	4
Adversarial Neural Pruning with Latent Vulnerability Suppression	✅	✅	✅	❌	❌	❌	✅	4
Adversarial Nonnegative Matrix Factorization	✅	❌	✅	❌	❌	❌	✅	3
Adversarial Risk via Optimal Transport and Optimal Couplings	❌	✅	✅	❌	❌	❌	❌	2
Adversarial Robustness Against the Union of Multiple Perturbation Models	✅	✅	✅	❌	✅	❌	✅	5
Adversarial Robustness for Code	✅	✅	✅	❌	✅	❌	✅	5
Adversarial Robustness via Runtime Masking and Cleansing	✅	✅	✅	✅	✅	❌	✅	6
Agent57: Outperforming the Atari Human Benchmark	❌	❌	✅	❌	❌	❌	✅	2
Aggregation of Multiple Knockoffs	✅	❌	✅	❌	❌	❌	✅	3
Aligned Cross Entropy for Non-Autoregressive Machine Translation	✅	❌	✅	✅	✅	❌	✅	5
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference	❌	✅	✅	❌	❌	❌	✅	3
Alleviating Privacy Attacks via Causal Learning	❌	✅	✅	❌	❌	✅	✅	4
Almost Tune-Free Variance Reduction	✅	❌	✅	❌	❌	❌	✅	3
Amortised Learning by Wake-Sleep	✅	✅	✅	❌	❌	❌	✅	4
Amortized Finite Element Analysis for Fast PDE-Constrained Optimization	❌	✅	❌	❌	❌	❌	✅	2
Amortized Population Gibbs Samplers with Neural Sufficient Statistics	✅	❌	✅	❌	❌	❌	✅	3
An Accelerated DFO Algorithm for Finite-sum Convex Functions	✅	❌	✅	❌	❌	❌	✅	3
An EM Approach to Non-autoregressive Conditional Sequence Generation	✅	❌	✅	✅	✅	❌	✅	5
An Explicitly Relational Neural Network Architecture	❌	✅	❌	❌	❌	❌	❌	1
An Imitation Learning Approach for Cache Replacement	✅	✅	✅	✅	❌	❌	✅	5
An Investigation of Why Overparameterization Exacerbates Spurious Correlations	❌	✅	✅	❌	❌	❌	✅	3
An Optimistic Perspective on Offline Reinforcement Learning	❌	✅	✅	❌	❌	❌	✅	3
An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm	✅	❌	❌	❌	❌	❌	✅	2
An end-to-end approach for the verification problem: learning the right distance	✅	✅	✅	✅	❌	❌	✅	5
Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks	❌	❌	✅	❌	✅	❌	✅	3
Anderson Acceleration of Proximal Gradient Methods	❌	❌	❌	❌	❌	❌	✅	1
Angular Visual Hardness	❌	❌	✅	✅	❌	❌	✅	3
Approximating Stacked and Bidirectional Recurrent Architectures with the Delayed Recurrent Neural Network	❌	✅	✅	✅	✅	✅	✅	6
Approximation Capabilities of Neural ODEs and Invertible Residual Networks	❌	❌	✅	✅	✅	❌	✅	4
Approximation Guarantees of Local Search Algorithms via Localizability of Set Functions	✅	❌	❌	❌	✅	❌	✅	3
Associative Memory in Iterated Overparameterized Sigmoid Autoencoders	❌	❌	✅	❌	✅	❌	✅	3
Asynchronous Coagent Networks	❌	❌	❌	❌	❌	❌	❌	0
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger	✅	❌	✅	❌	❌	❌	✅	3
Attentive Group Equivariant Convolutional Networks	❌	✅	✅	✅	❌	❌	✅	4
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks	✅	✅	✅	✅	✅	❌	✅	6
AutoML-Zero: Evolving Machine Learning Algorithms From Scratch	✅	✅	✅	✅	❌	❌	✅	5
Automated Synthetic-to-Real Generalization	✅	✅	✅	✅	❌	❌	✅	5
Automatic Reparameterisation of Probabilistic Programs	✅	✅	✅	❌	❌	❌	✅	4
Automatic Shortcut Removal for Self-Supervised Representation Learning	❌	❌	✅	✅	✅	❌	✅	4
BINOCULARS for efficient, nonmyopic sequential experimental design	✅	❌	✅	❌	❌	❌	✅	3
Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning	❌	❌	✅	❌	❌	❌	✅	2
Bandits for BMO Functions	✅	❌	❌	❌	❌	❌	✅	2
Bandits with Adversarial Scaling	✅	❌	❌	❌	❌	❌	❌	1
Batch Reinforcement Learning with Hyperparameter Gradients	❌	❌	✅	✅	❌	❌	✅	3
Batch Stationary Distribution Estimation	✅	❌	❌	❌	❌	❌	✅	2
Bayesian Differential Privacy for Machine Learning	❌	✅	✅	❌	❌	❌	❌	2
Bayesian Experimental Design for Implicit Models by Mutual Information Neural Estimation	❌	✅	❌	❌	❌	❌	✅	2
Bayesian Graph Neural Networks with Adaptive Connection Sampling	❌	✅	✅	✅	❌	❌	✅	4
Bayesian Learning from Sequential Data using Gaussian Processes with Signature Covariances	✅	✅	✅	✅	✅	✅	✅	7
Bayesian Optimisation over Multiple Continuous and Categorical Inputs	✅	✅	✅	❌	✅	❌	✅	5
Bayesian Sparsification of Deep C-valued Networks	❌	✅	✅	✅	❌	❌	✅	4
Being Bayesian about Categorical Probability	❌	✅	✅	✅	✅	❌	✅	5
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks	❌	✅	✅	✅	❌	❌	✅	4
Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting	✅	❌	❌	❌	❌	❌	✅	2
Better depth-width trade-offs for neural networks through the lens of dynamical systems	❌	❌	❌	❌	❌	❌	✅	1
Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?	❌	❌	✅	❌	✅	❌	✅	3
Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels	✅	✅	✅	✅	✅	❌	✅	6
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles	✅	❌	❌	❌	❌	❌	❌	1
Bidirectional Model-based Policy Optimization	✅	❌	✅	❌	❌	❌	❌	2
Bio-Inspired Hashing for Unsupervised Similarity Search	❌	❌	✅	✅	❌	❌	✅	3
Bisection-Based Pricing for Repeated Contextual Auctions against Strategic Buyer	✅	❌	❌	❌	❌	❌	❌	1
Black-Box Methods for Restoring Monotonicity	❌	❌	❌	❌	❌	❌	❌	0
Black-Box Variational Inference as a Parametric Approximation to Langevin Dynamics	❌	❌	✅	❌	✅	✅	✅	4
Black-box Certification and Learning under Adversarial Perturbations	❌	❌	❌	❌	❌	❌	❌	0
BoXHED: Boosted eXact Hazard Estimator with Dynamic covariates	✅	✅	✅	✅	❌	❌	✅	5
Boosted Histogram Transform for Regression	✅	❌	❌	✅	❌	❌	✅	3
Boosting Deep Neural Network Efficiency with Dual-Module Inference	✅	❌	✅	✅	✅	✅	✅	6
Boosting Frank-Wolfe by Chasing Gradients	✅	✅	✅	❌	✅	❌	✅	5
Boosting for Control of Dynamical Systems	✅	❌	❌	❌	❌	❌	✅	2
Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning	✅	❌	✅	❌	✅	❌	✅	4
Born-Again Tree Ensembles	✅	✅	✅	✅	✅	✅	✅	7
Bounding the fairness and accuracy of classifiers from population statistics	✅	✅	✅	✅	❌	❌	❌	4
Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning	✅	❌	❌	❌	❌	❌	❌	1
Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search	✅	✅	✅	✅	❌	❌	✅	5
Bridging the Gap Between f-GANs and Wasserstein GANs	✅	✅	✅	✅	❌	✅	✅	6
Budgeted Online Influence Maximization	✅	❌	✅	❌	❌	❌	✅	3
CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods	✅	✅	✅	✅	❌	❌	❌	4
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information	✅	✅	✅	❌	❌	❌	✅	4
CURL: Contrastive Unsupervised Representations for Reinforcement Learning	✅	✅	✅	❌	❌	❌	✅	4
Calibration, Entropy Rates, and Memory in Language Models	✅	❌	✅	❌	❌	❌	❌	2
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?	✅	✅	✅	✅	❌	❌	✅	5
Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?	✅	✅	✅	✅	❌	❌	✅	5
Can Stochastic Zeroth-Order Frank-Wolfe Method Converge Faster for Non-Convex Problems?	✅	❌	✅	❌	❌	❌	✅	3
Causal Effect Estimation and Optimal Dose Suggestions in Mobile Health	❌	✅	✅	❌	❌	❌	✅	3
Causal Effect Identifiability under Partial-Observability	✅	❌	❌	❌	❌	❌	❌	1
Causal Inference using Gaussian Processes with Structured Latent Confounders	✅	❌	✅	❌	❌	❌	✅	3
Causal Modeling for Fairness In Dynamical Systems	❌	✅	❌	❌	❌	❌	❌	1
Causal Strategic Linear Regression	✅	❌	❌	❌	❌	❌	❌	1
Causal Structure Discovery from Distributions Arising from Mixtures of DAGs	✅	❌	✅	❌	❌	❌	✅	3
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings	✅	❌	✅	❌	❌	❌	✅	3
Certified Data Removal from Machine Learning Models	✅	✅	✅	❌	❌	❌	✅	4
Certified Robustness to Label-Flipping Attacks via Randomized Smoothing	✅	❌	✅	❌	❌	❌	❌	2
Channel Equilibrium Networks for Learning Deep Representation	❌	✅	✅	✅	✅	✅	✅	6
Characterizing Distribution Equivalence and Structure Learning for Cyclic and Acyclic Directed Graphs	❌	✅	❌	❌	❌	❌	✅	2
Choice Set Optimization Under Discrete Choice Models of Group Decisions	✅	✅	✅	❌	❌	❌	✅	4
Circuit-Based Intrinsic Methods to Detect Overfitting	❌	❌	✅	❌	✅	✅	✅	4
Class-Weighted Classification: Trade-offs and Robust Approaches	❌	✅	✅	❌	❌	❌	✅	3
Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies	✅	✅	✅	✅	❌	❌	✅	5
Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning	✅	✅	✅	✅	❌	❌	❌	4
Closing the convergence gap of SGD without replacement	❌	✅	❌	❌	❌	❌	✅	2
CoMic: Complementary Task Learning & Mimicry for Reusable Skills	❌	❌	✅	❌	❌	❌	✅	2
Collaborative Machine Learning with Incentive-Aware Model Rewards	❌	❌	✅	❌	❌	❌	❌	1
Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems	❌	✅	✅	❌	❌	❌	✅	3
Combinatorial Pure Exploration for Dueling Bandit	✅	❌	❌	❌	❌	❌	❌	1
Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction	❌	✅	❌	❌	✅	❌	✅	3
Communication-Efficient Distributed PCA by Riemannian Optimization	✅	❌	✅	❌	❌	❌	✅	3
Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks	✅	❌	✅	❌	❌	❌	✅	3
Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions	✅	❌	✅	❌	❌	❌	✅	3
Composable Sketches for Functions of Frequencies: Beyond the Worst Case	❌	❌	✅	❌	❌	❌	✅	2
Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximation	❌	✅	✅	❌	❌	❌	✅	3
Computational and Statistical Tradeoffs in Inferring Combinatorial Structures of Ising Model	❌	❌	❌	❌	❌	❌	❌	0
ConQUR: Mitigating Delusional Bias in Deep Q-Learning	✅	❌	✅	❌	❌	❌	✅	3
Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions	✅	❌	❌	❌	❌	❌	❌	1
Concept Bottleneck Models	❌	✅	✅	✅	❌	❌	✅	4
Concise Explanations of Neural Networks using Adversarial Training	❌	✅	✅	❌	❌	❌	❌	2
Conditional gradient methods for stochastically constrained convex minimization	✅	❌	✅	❌	❌	❌	✅	3
Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting	✅	✅	❌	❌	✅	❌	✅	4
Confidence-Aware Learning for Deep Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks	✅	✅	✅	✅	❌	❌	✅	5
Consistent Estimators for Learning to Defer to an Expert	❌	✅	✅	✅	❌	❌	✅	4
Consistent Structured Prediction with Max-Min Margin Markov Networks	✅	✅	✅	✅	❌	❌	✅	5
Constant Curvature Graph Convolutional Networks	❌	❌	✅	✅	❌	❌	✅	3
Constrained Markov Decision Processes via Backward Value Functions	✅	❌	✅	❌	❌	❌	✅	3
Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks	❌	❌	❌	❌	❌	❌	❌	0
Context Aware Local Differential Privacy	❌	❌	✅	❌	❌	❌	✅	2
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning	✅	✅	✅	❌	❌	❌	❌	3
Continuous Graph Neural Networks	❌	❌	✅	✅	❌	❌	❌	2
Continuous Time Bayesian Networks with Clocks	✅	❌	✅	❌	❌	❌	✅	3
Continuous-time Lower Bounds for Gradient-based Algorithms	❌	❌	❌	❌	❌	❌	✅	1
Continuously Indexed Domain Adaptation	❌	❌	✅	✅	❌	❌	✅	3
Contrastive Multi-View Representation Learning on Graphs	✅	❌	✅	✅	❌	❌	✅	4
Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning	✅	✅	✅	❌	❌	❌	✅	4
ControlVAE: Controllable Variational Autoencoder	✅	✅	✅	✅	❌	❌	✅	5
Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics	✅	✅	✅	❌	✅	❌	✅	5
Convergence Rates of Variational Inference in Sparse Deep Learning	❌	❌	❌	❌	❌	❌	❌	0
Convergence of a Stochastic Gradient Method with Momentum for Non-Smooth Non-Convex Optimization	✅	❌	❌	❌	❌	❌	✅	2
Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer Games	✅	❌	✅	❌	✅	✅	✅	5
Convex Calibrated Surrogates for the Multi-Label F-Measure	✅	❌	✅	✅	❌	❌	✅	4
Convex Representation Learning for Generalized Invariance in Semi-Inner-Product Space	❌	❌	✅	❌	❌	❌	✅	2
Convolutional Kernel Networks for Graph-Structured Data	✅	✅	✅	✅	❌	❌	✅	5
Convolutional dictionary learning based auto-encoders for natural exponential-family distributions	✅	✅	✅	✅	❌	❌	✅	5
Cooperative Multi-Agent Bandits with Heavy Tails	✅	❌	✅	❌	❌	❌	✅	3
Coresets for Clustering in Graphs of Bounded Treewidth	✅	✅	✅	❌	✅	❌	✅	5
Coresets for Data-efficient Training of Machine Learning Models	✅	❌	✅	❌	❌	❌	✅	3
Correlation Clustering with Asymmetric Classification Errors	✅	❌	❌	❌	❌	❌	❌	1
Cost-Effective Interactive Attention Learning with Neural Attention Processes	✅	✅	✅	✅	❌	❌	❌	4
Cost-effectively Identifying Causal Effects When Only Response Variable is Observable	✅	❌	✅	❌	❌	❌	✅	3
Counterfactual Cross-Validation: Stable Model Selection Procedure for Causal Inference Models	✅	✅	✅	✅	❌	❌	❌	4
Countering Language Drift with Seeded Iterated Learning	✅	✅	✅	❌	❌	❌	✅	4
Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness	❌	✅	✅	❌	❌	❌	✅	3
Curvature-corrected learning dynamics in deep neural networks	❌	❌	❌	❌	❌	❌	✅	1
Customizing ML Predictions for Online Algorithms	✅	❌	❌	✅	❌	❌	✅	3
DINO: Distributed Newton-Type Optimization Method	✅	✅	✅	❌	❌	❌	✅	4
DROCC: Deep Robust One-Class Classification	✅	✅	✅	✅	✅	✅	✅	7
DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images	❌	❌	✅	❌	❌	❌	✅	2
Data Amplification: Instance-Optimal Property Estimation	❌	❌	❌	❌	❌	❌	✅	1
Data Valuation using Reinforcement Learning	✅	✅	✅	✅	❌	❌	✅	5
Data preprocessing to mitigate bias: A maximum entropy based approach	✅	✅	✅	✅	✅	❌	✅	6
Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models	✅	❌	✅	❌	❌	❌	✅	3
Data-Efficient Image Recognition with Contrastive Predictive Coding	❌	❌	✅	❌	❌	❌	✅	2
DeBayes: a Bayesian Method for Debiasing Network Embeddings	❌	❌	✅	✅	❌	✅	✅	4
Debiased Sinkhorn barycenters	✅	✅	✅	✅	✅	❌	✅	6
Decentralised Learning with Random Features and Distributed Gradient Descent	❌	❌	✅	❌	❌	❌	✅	2
Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions	✅	✅	✅	❌	❌	❌	❌	3
Decision Trees for Decision-Making under the Predict-then-Optimize Framework	❌	✅	✅	✅	❌	❌	✅	4
Decoupled Greedy Learning of CNNs	✅	✅	✅	❌	❌	❌	✅	4
Deep Coordination Graphs	✅	✅	❌	❌	❌	❌	✅	3
Deep Divergence Learning	❌	✅	✅	✅	❌	❌	✅	4
Deep Gaussian Markov Random Fields	✅	✅	✅	❌	✅	❌	❌	4
Deep Graph Random Process for Relational-Thinking-Based Speech Recognition	❌	❌	✅	✅	✅	❌	✅	4
Deep Isometric Learning for Visual Recognition	❌	✅	✅	✅	❌	❌	✅	4
Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks	✅	❌	✅	✅	❌	❌	✅	4
Deep PQR: Solving Inverse Reinforcement Learning using Anchor Actions	✅	❌	✅	❌	❌	❌	✅	3
Deep Reasoning Networks for Unsupervised Pattern De-mixing with Constraint Reasoning	✅	❌	✅	✅	✅	❌	✅	5
Deep Reinforcement Learning with Robust and Smooth Policy	✅	❌	✅	❌	❌	❌	✅	3
Deep Streaming Label Learning	❌	❌	✅	✅	✅	❌	❌	3
Deep k-NN for Noisy Labels	✅	❌	✅	✅	✅	✅	✅	6
DeepCoDA: personalized interpretability for compositional health data	❌	✅	✅	✅	❌	❌	✅	4
DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training	✅	❌	✅	❌	❌	❌	✅	3
Defense Through Diverse Directions	❌	❌	✅	❌	❌	❌	✅	2
DeltaGrad: Rapid retraining of machine learning models	✅	✅	✅	❌	✅	✅	✅	6
Description Based Text Classification with Reinforcement Learning	❌	❌	✅	❌	❌	❌	❌	1
Designing Optimal Dynamic Treatment Regimes: A Causal Reinforcement Learning Approach	✅	❌	✅	❌	❌	❌	❌	2
DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths	✅	✅	✅	❌	❌	❌	✅	4
Detecting Out-of-Distribution Examples with Gram Matrices	✅	✅	✅	✅	❌	❌	❌	4
Differentiable Likelihoods for Fast Inversion of ’Likelihood-Free’ Dynamical Systems	✅	❌	❌	❌	❌	❌	✅	2
Differentiable Product Quantization for End-to-End Embedding Compression	✅	✅	✅	❌	✅	❌	✅	5
Differentially Private Set Union	✅	✅	❌	❌	❌	❌	✅	3
Differentiating through the Fréchet Mean	✅	✅	✅	✅	✅	❌	✅	6
Discount Factor as a Regularizer in Reinforcement Learning	✅	✅	✅	❌	❌	❌	✅	4
Discriminative Adversarial Search for Abstractive Summarization	✅	❌	✅	✅	✅	❌	✅	5
Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions	✅	❌	✅	❌	❌	❌	✅	3
Disentangling Trainability and Generalization in Deep Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation	❌	✅	✅	✅	❌	❌	✅	4
Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation	❌	❌	✅	❌	❌	❌	✅	2
Distance Metric Learning with Joint Representation Diversification	❌	✅	✅	✅	✅	❌	✅	5
Distinguishing Cause from Effect Using Quantiles: Bivariate Quantile Causal Discovery	❌	✅	✅	❌	❌	✅	✅	4
Distributed Online Optimization over a Heterogeneous Network with Any-Batch Mirror Descent	❌	❌	✅	❌	❌	❌	❌	1
Distribution Augmentation for Generative Modeling	❌	✅	✅	✅	❌	❌	✅	4
Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits	✅	❌	❌	✅	❌	❌	✅	3
Divide and Conquer: Leveraging Intermediate Feature Representations for Quantized Training of Neural Networks	✅	❌	✅	❌	❌	❌	❌	2
Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support	✅	❌	❌	❌	❌	❌	❌	1
Do GANs always have Nash equilibria?	✅	❌	✅	❌	❌	❌	✅	3
Do RNN and LSTM have Long Memory?	❌	✅	✅	✅	❌	❌	✅	4
Do We Need Zero Training Loss After Achieving Zero Training Error?	✅	✅	✅	✅	✅	❌	✅	6
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation	✅	✅	✅	✅	❌	❌	✅	5
Does label smoothing mitigate label noise?	❌	❌	✅	❌	❌	❌	✅	2
Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making	✅	✅	✅	✅	✅	❌	✅	6
Domain Adaptive Imitation Learning	✅	❌	✅	❌	❌	❌	❌	2
Domain Aggregation Networks for Multi-Source Domain Adaptation	✅	✅	✅	✅	❌	❌	❌	4
Don’t Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript	✅	❌	✅	❌	❌	❌	✅	3
Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation	❌	❌	✅	❌	❌	❌	✅	2
Double Trouble in Double Descent: Bias and Variance(s) in the Lazy Regime	❌	✅	✅	❌	❌	❌	✅	3
Double-Loop Unadjusted Langevin Algorithm	✅	❌	❌	❌	❌	❌	❌	1
Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables	✅	❌	✅	❌	✅	❌	✅	4
Doubly robust off-policy evaluation with shrinkage	❌	❌	✅	✅	❌	❌	✅	3
DropNet: Reducing Neural Network Complexity via Iterative Pruning	✅	✅	✅	✅	❌	❌	✅	5
Dual Mirror Descent for Online Allocation Problems	✅	✅	✅	❌	❌	❌	✅	4
Dual-Path Distillation: A Unified Framework to Improve Black-Box Attacks	✅	❌	✅	✅	❌	❌	✅	4
Duality in RKHSs with Infinite Dimensional Outputs: Application to Robust Losses	✅	❌	✅	✅	❌	❌	❌	3
Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising	✅	❌	❌	❌	❌	❌	❌	1
Dynamics of Deep Neural Networks and Neural Tangent Hierarchy	❌	❌	❌	❌	❌	❌	❌	0
ECLIPSE: An Extreme-Scale Linear Program Solver for Web-Applications	✅	❌	❌	❌	❌	✅	❌	2
Educating Text Autoencoders: Latent Representation Guidance via Denoising	❌	✅	✅	✅	❌	❌	✅	4
Efficient Continuous Pareto Exploration in Multi-Task Learning	✅	✅	✅	❌	❌	❌	✅	4
Efficient Domain Generalization via Common-Specific Low-Rank Decomposition	✅	✅	✅	✅	❌	✅	✅	6
Efficient Identification in Linear Structural Causal Models with Auxiliary Cutsets	✅	❌	❌	❌	❌	❌	❌	1
Efficient Intervention Design for Causal Discovery with Latents	✅	❌	❌	❌	❌	❌	✅	2
Efficient Non-conjugate Gaussian Process Factor Models for Spike Count Data using Polynomial Approximations	❌	✅	✅	❌	❌	❌	✅	3
Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation	✅	❌	❌	❌	❌	❌	❌	1
Efficient Policy Learning from Surrogate-Loss Classification Reductions	❌	❌	✅	✅	❌	❌	✅	3
Efficient Proximal Mapping of the 1-path-norm of Shallow Networks	✅	❌	✅	❌	❌	❌	✅	3
Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More	✅	✅	✅	✅	❌	❌	✅	5
Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors	❌	✅	✅	❌	❌	❌	✅	3
Efficient nonparametric statistical inference on population feature importance using Shapley values	✅	✅	✅	✅	✅	❌	✅	6
Efficiently Learning Adversarially Robust Halfspaces with Noise	❌	❌	❌	❌	❌	❌	❌	0
Efficiently Solving MDPs with Stochastic Mirror Descent	✅	❌	❌	❌	❌	❌	❌	1
Efficiently sampling functions from Gaussian process posteriors	❌	✅	❌	❌	❌	❌	✅	2
Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits	✅	✅	✅	✅	✅	❌	✅	6
Eliminating the Invariance on the Loss Landscape of Linear Autoencoders	❌	❌	✅	❌	❌	❌	✅	2
Emergence of Separable Manifolds in Deep Language Representations	❌	✅	✅	✅	❌	❌	❌	3
Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models	❌	❌	✅	✅	❌	❌	✅	3
Encoding Musical Style with Transformer Autoencoders	❌	✅	✅	✅	❌	❌	✅	4
Energy-Based Processes for Exchangeable Data	✅	✅	✅	❌	❌	❌	❌	3
Enhanced POET: Open-ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions	✅	✅	✅	❌	❌	❌	✅	4
Enhancing Simple Models by Exploiting What They Already Know	✅	❌	✅	✅	❌	✅	✅	5
Entropy Minimization In Emergent Languages	❌	✅	✅	✅	❌	❌	✅	4
Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities	❌	❌	❌	❌	❌	❌	✅	1
Equivariant Neural Rendering	❌	✅	✅	✅	✅	❌	✅	5
Error Estimation for Sketched SVD via the Bootstrap	✅	❌	✅	❌	❌	❌	✅	3
Error-Bounded Correction of Noisy Labels	✅	✅	✅	✅	❌	❌	✅	5
Estimating Generalization under Distribution Shifts via Domain-Invariant Representations	✅	✅	✅	❌	❌	❌	❌	3
Estimating Model Uncertainty of Neural Networks in Sparse Information Form	✅	✅	✅	✅	✅	❌	✅	6
Estimating Q(s,s’) with Deep Deterministic Dynamics Gradients	✅	✅	✅	❌	❌	❌	❌	3
Estimating the Error of Randomized Newton Methods: A Bootstrap Approach	✅	❌	✅	❌	❌	❌	✅	3
Estimating the Number and Effect Sizes of Non-null Hypotheses	❌	✅	✅	❌	❌	❌	✅	3
Estimation of Bounds on Potential Outcomes For Decision Making	✅	✅	✅	✅	❌	❌	✅	5
Evaluating Lossy Compression Rates of Deep Generative Models	❌	✅	✅	❌	❌	❌	✅	3
Evaluating Machine Accuracy on ImageNet	❌	❌	✅	✅	❌	❌	✅	3
Evaluating the Performance of Reinforcement Learning Algorithms	✅	✅	✅	❌	❌	❌	✅	4
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination	✅	✅	✅	❌	❌	❌	✅	4
Evolutionary Topology Search for Tensor Network Decomposition	✅	✅	✅	❌	✅	❌	✅	5
Expert Learning through Generalized Inverse Multiobjective Optimization: Models, Insights, and Algorithms	✅	❌	❌	❌	❌	❌	❌	1
Explainable and Discourse Topic-aware Neural Language Understanding	✅	✅	✅	❌	❌	❌	✅	4
Explainable k-Means and k-Medians Clustering	✅	❌	❌	❌	❌	❌	❌	1
Explaining Groups of Points in Low-Dimensional Representations	✅	✅	✅	❌	❌	❌	✅	4
Explicit Gradient Learning for Black-Box Optimization	✅	✅	✅	❌	❌	❌	✅	4
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits	✅	❌	❌	❌	❌	❌	✅	2
Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills	❌	✅	❌	❌	❌	❌	❌	1
Extra-gradient with player sampling for faster convergence in n-player games	✅	✅	✅	❌	❌	❌	✅	4
Extrapolation for Large-batch Training in Deep Learning	✅	❌	✅	✅	❌	❌	✅	4
Extreme Multi-label Classification from Aggregated Labels	✅	❌	✅	✅	❌	❌	❌	3
FACT: A Diagnostic for Group Fairness Trade-offs	❌	✅	✅	❌	❌	❌	❌	2
FR-Train: A Mutual Information-Based Approach to Fair and Robust Training	❌	✅	✅	✅	✅	❌	✅	5
Fair Generative Modeling via Weak Supervision	✅	✅	✅	✅	❌	✅	✅	6
Fair Learning with Private Demographic Data	✅	✅	✅	✅	❌	❌	✅	5
Fair k-Centers via Maximum Matching	✅	❌	✅	❌	✅	❌	✅	4
Fairwashing explanations with off-manifold detergent	❌	✅	✅	✅	✅	❌	✅	5
Familywise Error Rate Control by Interactive Unmasking	✅	✅	✅	❌	❌	✅	✅	5
Fast Adaptation to New Environments via Policy-Dynamics Value Functions	❌	✅	✅	✅	❌	❌	✅	4
Fast Deterministic CUR Matrix Decomposition with Accuracy Assurance	✅	❌	✅	❌	✅	❌	✅	4
Fast Differentiable Sorting and Ranking	❌	✅	✅	✅	✅	❌	✅	5
Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case	✅	❌	❌	❌	❌	❌	✅	2
Fast OSCAR and OWL Regression via Safe Screening Rules	✅	❌	✅	❌	✅	❌	✅	4
Fast and Consistent Learning of Hidden Markov Models by Incorporating Non-Consecutive Correlations	❌	❌	❌	❌	❌	✅	❌	1
Fast and Private Submodular and $k$-Submodular Functions Maximization with Matroid Constraints	✅	❌	❌	❌	❌	❌	❌	1
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods	✅	✅	✅	✅	❌	❌	❌	4
Fast computation of Nash Equilibria in Imperfect Information Games	❌	❌	❌	❌	❌	❌	✅	1
Faster Graph Embeddings via Coarsening	✅	❌	✅	✅	✅	❌	✅	5
Feature Noise Induces Loss Discrepancy Across Groups	❌	✅	✅	❌	❌	❌	✅	3
Feature Quantization Improves GAN Training	✅	✅	✅	❌	✅	❌	✅	5
Feature Selection using Stochastic Gates	✅	✅	✅	✅	❌	❌	✅	5
Feature-map-level Online Adversarial Knowledge Distillation	❌	❌	✅	❌	❌	❌	✅	2
FedBoost: A Communication-Efficient Algorithm for Federated Learning	✅	❌	✅	❌	❌	❌	✅	3
Federated Learning with Only Positive Labels	✅	❌	✅	❌	❌	❌	✅	3
FetchSGD: Communication-Efficient Federated Learning with Sketching	✅	✅	✅	✅	❌	❌	✅	5
Few-shot Domain Adaptation by Causal Mechanism Transfer	✅	❌	✅	✅	✅	❌	✅	5
Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs	✅	❌	✅	✅	❌	❌	✅	4
Fiduciary Bandits	✅	❌	❌	❌	❌	❌	❌	1
Fiedler Regularization: Learning Neural Networks with Graph Sparsity	✅	✅	✅	❌	✅	✅	✅	6
Finding trainable sparse networks through Neural Tangent Transfer	❌	❌	✅	❌	❌	❌	✅	2
Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent	❌	❌	❌	❌	❌	❌	❌	0
Finite-Time Convergence in Continuous-Time Optimization	❌	❌	❌	❌	❌	❌	✅	1
Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games	✅	❌	❌	❌	❌	❌	❌	1
Flexible and Efficient Long-Range Planning Through Curious Exploration	✅	❌	❌	❌	❌	❌	❌	1
Forecasting Sequential Data Using Consistent Koopman Autoencoders	❌	✅	✅	❌	❌	❌	✅	3
FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis	✅	✅	❌	❌	❌	❌	✅	3
Fractal Gaussian Networks: A sparse random graph model based on Gaussian Multiplicative Chaos	❌	❌	❌	❌	❌	❌	❌	0
Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise	❌	✅	✅	❌	❌	❌	✅	3
Frequency Bias in Neural Networks for Input of Non-Uniform Density	❌	❌	❌	❌	❌	❌	❌	0
Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions	✅	❌	✅	❌	❌	❌	✅	3
From Chaos to Order: Symmetry and Conservation Laws in Game Dynamics	❌	❌	❌	❌	❌	❌	❌	0
From ImageNet to Image Classification: Contextualizing Progress on Benchmarks	❌	❌	✅	✅	❌	❌	❌	2
From Importance Sampling to Doubly Robust Policy Gradient	❌	❌	✅	❌	❌	❌	✅	2
From Local SGD to Local Fixed-Point Methods for Federated Learning	✅	❌	✅	❌	✅	❌	✅	4
From PAC to Instance-Optimal Sample Complexity in the Plackett-Luce Model	✅	❌	❌	❌	❌	❌	✅	2
From Sets to Multisets: Provable Variational Inference for Probabilistic Integer Submodular Models	✅	❌	✅	❌	❌	❌	✅	3
Frustratingly Simple Few-Shot Object Detection	❌	✅	✅	❌	❌	❌	✅	3
Full Law Identification in Graphical Models of Missing Data: Completeness Results	❌	❌	❌	❌	❌	❌	❌	0
Fully Parallel Hyperparameter Search: Reshaped Space-Filling	❌	✅	✅	✅	❌	❌	✅	4
Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations	✅	✅	✅	❌	❌	❌	❌	3
GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation	❌	✅	✅	✅	✅	❌	✅	5
Gamification of Pure Exploration for Linear Bandits	✅	❌	❌	❌	❌	❌	✅	2
Generalisation error in learning with random features and the hidden manifold model	❌	❌	❌	❌	❌	❌	✅	1
Generalization Error of Generalized Linear Models in High Dimensions	✅	✅	❌	❌	❌	❌	✅	3
Generalization Guarantees for Sparse Kernel Approximation with Entropic Optimal Features	✅	❌	✅	✅	✅	❌	❌	4
Generalization and Representational Limits of Graph Neural Networks	❌	❌	❌	❌	❌	❌	❌	0
Generalization to New Actions in Reinforcement Learning	✅	✅	✅	✅	❌	❌	✅	5
Generalized and Scalable Optimal Sparse Decision Trees	✅	✅	✅	❌	❌	❌	✅	4
Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data	✅	✅	✅	✅	❌	❌	✅	5
Generating Programmatic Referring Expressions via Program Synthesis	✅	✅	✅	❌	❌	❌	✅	4
Generative Adversarial Imitation Learning with Neural Network Parameterization: Global Optimality and Convergence Rate	✅	❌	❌	❌	❌	❌	❌	1
Generative Flows with Matrix Exponential	✅	✅	✅	❌	✅	❌	✅	5
Generative Pretraining From Pixels	❌	❌	✅	✅	✅	❌	✅	4
Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data	❌	✅	✅	✅	✅	❌	✅	5
Global Concavity and Optimization in a Class of Dynamic Discrete Choice Models	✅	❌	❌	❌	❌	❌	✅	2
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks	✅	❌	✅	✅	❌	❌	✅	4
Goal-Aware Prediction: Learning to Model What Matters	✅	✅	✅	❌	❌	❌	✅	4
Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection	✅	✅	✅	✅	❌	❌	✅	5
Goodness-of-Fit Tests for Inhomogeneous Random Graphs	✅	❌	❌	❌	❌	❌	✅	2
Gradient Temporal-Difference Learning with Regularized Corrections	❌	✅	✅	❌	❌	❌	✅	3
Gradient-free Online Learning in Continuous Games with Delayed Rewards	✅	❌	❌	❌	❌	❌	❌	1
GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values	✅	✅	✅	❌	❌	❌	✅	4
Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters	❌	✅	✅	✅	❌	❌	✅	4
Graph Filtration Learning	❌	✅	✅	✅	❌	❌	✅	4
Graph Homomorphism Convolution	✅	✅	✅	✅	❌	❌	✅	5
Graph Optimal Transport for Cross-Domain Alignment	✅	✅	✅	✅	❌	❌	✅	5
Graph Random Neural Features for Distance-Preserving Graph Representations	❌	❌	✅	✅	❌	❌	✅	3
Graph Structure of Neural Networks	❌	❌	✅	✅	✅	❌	✅	4
Graph-based Nearest Neighbor Search: From Practice to Theory	❌	✅	✅	❌	✅	❌	❌	3
Graph-based, Self-Supervised Program Repair from Diagnostic Feedback	❌	✅	✅	✅	✅	❌	✅	5
GraphOpt: Learning Optimization Models of Graph Formation	✅	❌	✅	❌	❌	❌	✅	3
Graphical Models Meet Bandits: A Variational Thompson Sampling Approach	✅	❌	❌	❌	✅	❌	✅	3
Growing Action Spaces	❌	✅	❌	❌	❌	❌	✅	2
Growing Adaptive Multi-hyperplane Machines	✅	✅	✅	❌	✅	❌	✅	5
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization	✅	❌	✅	✅	❌	❌	✅	4
Haar Graph Pooling	✅	❌	✅	✅	✅	❌	✅	5
Hallucinative Topological Memory for Zero-Shot Visual Planning	❌	✅	❌	❌	❌	❌	✅	2
Handling the Positive-Definite Constraint in the Bayesian Learning Rule	✅	✅	✅	✅	❌	❌	✅	5
Harmonic Decompositions of Convolutional Networks	❌	❌	❌	❌	❌	❌	❌	0
Healing Products of Gaussian Process Experts	❌	✅	✅	❌	❌	❌	✅	3
Hierarchical Generation of Molecular Graphs using Structural Motifs	❌	✅	✅	✅	❌	❌	❌	3
Hierarchical Verification for Adversarial Robustness	✅	❌	✅	❌	✅	✅	✅	5
Hierarchically Decoupled Imitation For Morphological Transfer	✅	✅	✅	❌	❌	❌	❌	3
High-dimensional Robust Mean Estimation via Gradient Descent	✅	❌	❌	❌	❌	❌	❌	1
History-Gradient Aided Batch Size Adaptation for Variance Reduced Algorithms	✅	❌	✅	❌	❌	❌	✅	3
How Good is the Bayes Posterior in Deep Neural Networks Really?	✅	✅	✅	✅	❌	❌	✅	5
How recurrent networks implement contextual processing in sentiment analysis	❌	❌	✅	✅	❌	❌	✅	3
How to Solve Fair k-Center in Massive Data Models	✅	✅	✅	❌	✅	❌	✅	5
How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization	✅	❌	✅	❌	✅	❌	✅	4
Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization with Nearly Optimal Generalization	✅	❌	✅	❌	❌	❌	✅	3
Hypernetwork approach to generating point clouds	❌	✅	✅	❌	❌	❌	❌	2
IPBoost – Non-Convex Boosting via Integer Programming	✅	✅	✅	❌	✅	✅	✅	6
Identifying Statistical Bias in Dataset Replication	✅	✅	✅	❌	❌	❌	✅	4
Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation	✅	✅	✅	❌	✅	❌	✅	5
Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical Stability	✅	❌	✅	❌	❌	❌	✅	3
Implicit Generative Modeling for Efficient Exploration	✅	❌	✅	❌	❌	❌	❌	2
Implicit Geometric Regularization for Learning Shapes	❌	✅	✅	❌	❌	❌	✅	3
Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical Study	✅	❌	✅	❌	❌	❌	✅	3
Implicit Regularization of Random Feature Models	❌	❌	✅	❌	❌	❌	❌	1
Implicit competitive regularization in GANs	❌	❌	✅	❌	❌	❌	✅	2
Implicit differentiation of Lasso-type models for hyperparameter optimization	✅	✅	✅	✅	❌	❌	✅	5
Improved Communication Cost in Distributed PageRank Computation – A Theoretical Study	✅	❌	❌	❌	❌	❌	❌	1
Improved Optimistic Algorithms for Logistic Bandits	✅	❌	❌	❌	❌	❌	❌	1
Improved Sleeping Bandits with Stochastic Action Sets and Adversarial Rewards	✅	❌	❌	❌	❌	❌	✅	2
Improving Generative Imagination in Object-Centric World Models	❌	❌	✅	✅	❌	❌	✅	3
Improving Molecular Design by Stochastic Iterative Target Augmentation	✅	❌	✅	❌	❌	❌	✅	3
Improving Robustness of Deep-Learning-Based Image Reconstruction	✅	❌	✅	✅	❌	❌	✅	4
Improving Transformer Optimization Through Better Initialization	❌	✅	✅	❌	✅	❌	✅	4
Improving generalization by controlling label-noise information in neural network weights	✅	✅	✅	✅	❌	❌	✅	5
Improving the Gating Mechanism of Recurrent Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking	✅	❌	✅	❌	❌	❌	❌	2
Imputer: Sequence Modelling via Imputation and Dynamic Programming	❌	❌	✅	✅	❌	❌	✅	3
In Defense of Uniform Convergence: Generalization via Derandomization with an Application to Interpolating Predictors	❌	❌	❌	❌	❌	❌	❌	0
Incremental Sampling Without Replacement for Sequence Models	✅	✅	✅	❌	❌	❌	✅	4
Individual Calibration with Randomized Forecasting	❌	✅	✅	❌	❌	❌	✅	3
Individual Fairness for k-Clustering	✅	❌	✅	❌	❌	❌	✅	3
Inducing and Exploiting Activation Sparsity for Fast Inference on Deep Neural Networks	✅	❌	✅	✅	✅	✅	✅	6
Inductive Relation Prediction by Subgraph Reasoning	❌	✅	✅	✅	❌	❌	✅	4
Inductive-bias-driven Reinforcement Learning For Efficient Schedules in Heterogeneous Clusters	❌	❌	✅	❌	✅	❌	❌	2
Inertial Block Proximal Methods for Non-Convex Non-Smooth Optimization	✅	✅	✅	❌	✅	✅	✅	6
Inexact Tensor Methods with Dynamic Accuracies	✅	✅	✅	❌	✅	❌	✅	5
Inferring DQN structure for high-dimensional continuous control	✅	✅	✅	❌	❌	❌	✅	4
Infinite attention: NNGP and NTK for deep attention networks	❌	✅	✅	✅	❌	❌	❌	3
Influenza Forecasting Framework based on Gaussian Processes	✅	❌	✅	✅	❌	✅	✅	5
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs	✅	✅	✅	❌	❌	❌	✅	4
Information Particle Filter Tree: An Online Algorithm for POMDPs with Belief-Based Rewards on Continuous Domains	✅	✅	✅	❌	✅	❌	✅	5
Information-Theoretic Local Minima Characterization and Regularization	✅	✅	✅	✅	✅	❌	✅	6
Informative Dropout for Robust Representation Learning: A Shape-bias Perspective	✅	✅	✅	✅	❌	❌	❌	4
Input-Sparsity Low Rank Approximation in Schatten Norm	✅	❌	✅	❌	✅	✅	✅	5
InstaHide: Instance-hiding Schemes for Private Distributed Learning	✅	❌	✅	❌	❌	❌	✅	3
Inter-domain Deep Gaussian Processes	❌	✅	✅	❌	❌	❌	✅	3
Interference and Generalization in Temporal Difference Learning	❌	✅	✅	❌	❌	❌	✅	3
Interferometric Graph Transform: a Deep Unsupervised Graph Representation	❌	✅	✅	✅	❌	❌	✅	4
Interpolation between Residual and Non-Residual Networks	❌	❌	✅	❌	❌	❌	✅	2
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions	❌	✅	✅	❌	❌	❌	✅	3
Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failure	❌	✅	✅	✅	❌	❌	✅	4
Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge	❌	✅	✅	✅	❌	❌	✅	4
Interpreting Robust Optimization via Adversarial Influence Functions	❌	❌	✅	❌	❌	❌	✅	2
Intrinsic Reward Driven Imitation Learning via Generative Model	✅	✅	✅	❌	❌	❌	✅	4
Invariant Causal Prediction for Block MDPs	✅	✅	✅	❌	❌	❌	✅	4
Invariant Rationalization	❌	✅	✅	✅	❌	❌	✅	4
Invariant Risk Minimization Games	✅	✅	✅	❌	❌	❌	❌	3
Inverse Active Sensing: Modeling and Understanding Timely Decision-Making	✅	❌	❌	❌	❌	❌	✅	2
Invertible generative models for inverse problems: mitigating representation error and dataset bias	❌	❌	✅	❌	✅	❌	❌	2
Involutive MCMC: a Unifying Framework	✅	✅	✅	❌	❌	❌	✅	4
Is Local SGD Better than Minibatch SGD?	❌	❌	❌	❌	❌	❌	✅	1
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing	❌	❌	❌	❌	❌	❌	❌	0
It’s Not What Machines Can Learn, It’s What We Cannot Teach	❌	❌	❌	❌	✅	❌	✅	2
Kernel Methods for Cooperative Multi-Agent Contextual Bandits	✅	❌	✅	❌	❌	❌	✅	3
Kernel interpolation with continuous volume sampling	❌	❌	❌	❌	❌	❌	✅	1
Kernelized Stein Discrepancy Tests of Goodness-of-fit for Time-to-Event Data	❌	❌	✅	❌	❌	❌	✅	2
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning	✅	✅	❌	❌	❌	❌	❌	2
Knowing The What But Not The Where in Bayesian Optimization	✅	✅	✅	❌	❌	❌	✅	4
LEEP: A New Measure to Evaluate Transferability of Learned Representations	❌	❌	✅	❌	❌	❌	✅	2
LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction	✅	✅	✅	❌	❌	❌	❌	3
LTF: A Label Transformation Framework for Correcting Label Shift	❌	❌	✅	❌	❌	❌	✅	2
Label-Noise Robust Domain Adaptation	❌	❌	✅	✅	✅	❌	✅	4
Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks	❌	❌	✅	❌	❌	❌	✅	2
Laplacian Regularized Few-Shot Learning	✅	✅	✅	✅	✅	❌	✅	6
Latent Bernoulli Autoencoder	✅	✅	✅	❌	❌	❌	✅	4
Latent Space Factorisation and Manipulation via Matrix Subspace Projection	❌	✅	✅	❌	✅	❌	✅	4
Latent Variable Modelling with Hyperbolic Normalizing Flows	❌	✅	✅	❌	❌	❌	✅	3
Layered Sampling for Robust Optimization Problems	✅	❌	❌	❌	❌	❌	❌	1
LazyIter: A Fast Algorithm for Counting Markov Equivalent DAGs and Designing Experiments	✅	✅	❌	❌	❌	❌	❌	2
Learnable Group Transform For Time-Series	❌	✅	✅	❌	❌	❌	✅	3
Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition	✅	❌	❌	❌	❌	❌	❌	1
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization	✅	✅	✅	❌	❌	❌	✅	4
Learning Algebraic Multigrid Using Graph Neural Networks	✅	✅	❌	❌	✅	❌	✅	4
Learning Autoencoders with Relational Regularization	✅	✅	✅	✅	✅	❌	✅	6
Learning Calibratable Policies using Programmatic Style-Consistency	✅	✅	✅	✅	✅	✅	✅	7
Learning Compound Tasks without Task-specific Knowledge via Imitation and Self-supervised Learning	❌	❌	✅	❌	✅	❌	❌	2
Learning De-biased Representations with Biased Representations	❌	✅	✅	✅	❌	❌	✅	4
Learning Deep Kernels for Non-Parametric Two-Sample Tests	✅	✅	✅	❌	✅	❌	✅	5
Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information	✅	✅	✅	✅	✅	❌	✅	6
Learning Efficient Multi-agent Communication: An Information Bottleneck Approach	✅	✅	✅	❌	❌	❌	✅	4
Learning Factorized Weight Matrix for Joint Filtering	❌	❌	✅	❌	❌	❌	✅	2
Learning Fair Policies in Multi-Objective (Deep) Reinforcement Learning with Average and Discounted Rewards	❌	❌	❌	❌	✅	❌	❌	1
Learning Flat Latent Manifolds with VAEs	✅	❌	✅	❌	❌	❌	✅	3
Learning Human Objectives by Evaluating Hypothetical Behavior	✅	❌	✅	❌	❌	❌	❌	2
Learning Mixtures of Graphs from Epidemic Cascades	✅	❌	❌	❌	❌	❌	✅	2
Learning Near Optimal Policies with Low Inherent Bellman Error	✅	❌	❌	❌	❌	❌	❌	1
Learning Opinions in Social Networks	✅	❌	❌	❌	❌	❌	❌	1
Learning Optimal Tree Models under Beam Search	✅	❌	✅	✅	✅	❌	✅	5
Learning Portable Representations for High-Level Planning	❌	❌	❌	❌	❌	❌	❌	0
Learning Quadratic Games on Networks	✅	❌	✅	❌	❌	✅	✅	4
Learning Reasoning Strategies in End-to-End Differentiable Proving	✅	✅	✅	✅	❌	❌	✅	5
Learning Representations that Support Extrapolation	❌	❌	✅	❌	❌	❌	✅	2
Learning Robot Skills with Temporal Variational Inference	✅	✅	✅	❌	❌	❌	✅	4
Learning Selection Strategies in Buchberger’s Algorithm	✅	❌	❌	❌	✅	❌	✅	3
Learning Similarity Metrics for Numerical Simulations	❌	✅	✅	❌	❌	❌	✅	3
Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective	✅	❌	✅	❌	❌	❌	✅	3
Learning Task-Agnostic Embedding of Multiple Black-Box Experts for Multi-Task Model Fusion	✅	❌	✅	❌	❌	❌	❌	2
Learning To Stop While Learning To Predict	✅	✅	✅	✅	❌	❌	✅	5
Learning What to Defer for Maximum Independent Sets	❌	❌	✅	❌	✅	❌	❌	2
Learning and Evaluating Contextual Embedding of Source Code	❌	✅	✅	✅	✅	❌	✅	5
Learning and Sampling of Atomic Interventions from Observations	✅	❌	❌	❌	❌	❌	❌	1
Learning disconnected manifolds: a no GAN’s land	❌	❌	✅	❌	❌	❌	✅	2
Learning for Dose Allocation in Adaptive Clinical Trials with Safety Constraints	✅	❌	✅	❌	❌	❌	✅	3
Learning from Irregularly-Sampled Time Series: A Missing Data Perspective	❌	✅	✅	✅	❌	❌	✅	4
Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling	✅	❌	✅	✅	❌	❌	✅	4
Learning the Valuations of a $k$-demand Agent	✅	❌	❌	❌	❌	❌	✅	2
Learning the piece-wise constant graph structure of a varying Ising model	❌	✅	✅	✅	❌	❌	✅	4
Learning to Branch for Multi-Task Learning	❌	❌	✅	✅	✅	❌	✅	4
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules	✅	❌	✅	✅	❌	❌	✅	4
Learning to Encode Position for Transformer with Continuous Dynamical Model	❌	❌	✅	✅	❌	❌	✅	3
Learning to Learn Kernels with Variational Random Features	❌	❌	✅	❌	❌	❌	✅	2
Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning	✅	✅	✅	✅	❌	✅	✅	6
Learning to Rank Learning Curves	✅	❌	✅	✅	❌	❌	✅	4
Learning to Score Behaviors for Guided Policy Optimization	✅	✅	✅	❌	❌	❌	✅	4
Learning to Simulate Complex Physics with Graph Networks	❌	✅	✅	✅	❌	✅	✅	5
Learning to Simulate and Design for Structural Engineering	❌	❌	❌	✅	✅	❌	✅	3
Learning with Bounded Instance and Label-dependent Label Noise	✅	❌	✅	❌	❌	❌	✅	3
Learning with Feature and Distribution Evolvable Streams	❌	❌	✅	❌	❌	❌	✅	2
Learning with Good Feature Representations in Bandits and in RL with a Generative Model	✅	❌	❌	❌	❌	❌	❌	1
Learning with Multiple Complementary Labels	❌	❌	✅	✅	✅	❌	✅	4
Let’s Agree to Agree: Neural Networks Share Classification Order on Real Datasets	❌	❌	✅	✅	❌	❌	❌	2
Leveraging Frequency Analysis for Deep Fake Image Recognition	❌	✅	✅	✅	✅	❌	✅	5
Leveraging Procedural Generation to Benchmark Reinforcement Learning	❌	✅	✅	❌	❌	❌	✅	3
Lifted Disjoint Paths with Application in Multiple Object Tracking	✅	✅	✅	✅	❌	✅	✅	6
Likelihood-free MCMC with Amortized Approximate Ratio Estimators	✅	✅	❌	❌	❌	❌	✅	3
Linear Convergence of Randomized Primal-Dual Coordinate Method for Large-scale Linear Constrained Convex Programming	✅	❌	✅	❌	✅	✅	✅	5
Linear Lower Bounds and Conditioning of Differentiable Games	❌	❌	❌	❌	❌	❌	❌	0
Linear Mode Connectivity and the Lottery Ticket Hypothesis	✅	❌	✅	❌	❌	❌	✅	3
Linear bandits with Stochastic Delayed Feedback	✅	✅	✅	❌	❌	❌	✅	4
Logarithmic Regret for Adversarial Online Control	✅	❌	❌	❌	❌	❌	❌	1
Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently	✅	❌	❌	❌	❌	❌	❌	1
Logistic Regression for Massive Data with Rare Events	❌	❌	❌	❌	❌	❌	❌	0
Lookahead-Bounded Q-learning	✅	✅	❌	❌	❌	❌	✅	3
Lorentz Group Equivariant Neural Network for Particle Physics	❌	❌	✅	✅	✅	❌	✅	4
Loss Function Search for Face Recognition	✅	✅	✅	✅	✅	❌	✅	6
Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks	✅	❌	✅	❌	❌	❌	❌	2
Low-Rank Bottleneck in Multi-head Attention Models	❌	❌	✅	✅	❌	❌	✅	3
Low-Variance and Zero-Variance Baselines for Extensive-Form Games	✅	✅	✅	❌	❌	❌	✅	4
Low-loss connection of weight vectors: distribution-based approaches	❌	✅	✅	❌	❌	❌	✅	3
LowFER: Low-rank Bilinear Pooling for Link Prediction	❌	❌	✅	❌	❌	❌	✅	2
Lower Complexity Bounds for Finite-Sum Convex-Concave Minimax Optimization Problems	❌	❌	❌	❌	❌	❌	❌	0
Manifold Identification for Ultimately Communication-Efficient Distributed Optimization	✅	✅	✅	❌	✅	❌	✅	5
Mapping natural-language problems to formal-language solutions using structured neural representations	❌	❌	✅	❌	❌	❌	❌	1
Margin-aware Adversarial Domain Adaptation with Optimal Transport	❌	✅	✅	✅	❌	❌	✅	4
Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning	✅	✅	✅	❌	❌	❌	✅	4
Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptation	❌	✅	✅	✅	❌	❌	✅	4
Maximum-and-Concatenation Networks	❌	❌	✅	❌	❌	❌	❌	1
Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics	❌	✅	❌	❌	❌	✅	❌	2
Median Matrix Completion: from Embarrassment to Optimality	✅	❌	✅	✅	❌	❌	✅	4
Message Passing Least Squares Framework and its Application to Rotation Synchronization	✅	❌	✅	❌	✅	❌	✅	4
Meta Variance Transfer: Learning to Augment from the Others	✅	❌	✅	✅	✅	❌	✅	5
Meta-Learning with Shared Amortized Variational Inference	❌	✅	✅	✅	❌	❌	✅	4
Meta-learning for Mixed Linear Regression	✅	❌	❌	❌	❌	❌	✅	2
Meta-learning with Stochastic Linear Bandits	✅	❌	✅	❌	❌	❌	✅	3
MetaFun: Meta-Learning with Iterative Functional Updates	❌	✅	✅	✅	❌	❌	✅	4
Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks	✅	✅	✅	❌	❌	❌	✅	4
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack	✅	✅	✅	✅	❌	❌	✅	5
Minimax Pareto Fairness: A Multi Objective Perspective	✅	✅	✅	❌	❌	❌	✅	4
Minimax Rate for Learning From Pairwise Comparisons in the BTL Model	✅	❌	❌	❌	❌	❌	✅	2
Minimax Weight and Q-Function Learning for Off-Policy Evaluation	❌	❌	✅	❌	❌	❌	❌	1
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation	✅	❌	❌	❌	❌	❌	❌	1
Missing Data Imputation using Optimal Transport	✅	✅	✅	❌	❌	❌	✅	4
Mix-n-Match : Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning	❌	✅	✅	✅	❌	❌	❌	3
MoNet3D: Towards Accurate Monocular 3D Object Localization in Real Time	❌	✅	✅	❌	✅	❌	✅	4
Model Fusion with Kullback-Leibler Divergence	❌	✅	✅	❌	❌	❌	✅	3
Model-Based Reinforcement Learning with Value-Targeted Regression	✅	❌	❌	❌	❌	❌	✅	2
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes	✅	❌	❌	❌	❌	❌	❌	1
Modulating Surrogates for Bayesian Optimization	❌	❌	✅	❌	❌	❌	✅	2
Momentum Improves Normalized SGD	✅	❌	✅	❌	✅	❌	✅	4
Momentum-Based Policy Gradient Methods	✅	✅	✅	❌	❌	❌	✅	4
Moniqua: Modulo Quantized Communication in Decentralized SGD	✅	❌	✅	❌	✅	❌	✅	4
Monte-Carlo Tree Search as Regularized Policy Optimization	❌	❌	✅	❌	✅	❌	✅	3
More Data Can Expand The Generalization Gap Between Adversarially Robust and Standard Models	❌	❌	❌	❌	❌	❌	❌	0
More Information Supervised Probabilistic Deep Face Embedding Learning	✅	❌	✅	❌	✅	❌	✅	4
Multi-Agent Determinantal Q-Learning	✅	✅	✅	❌	❌	❌	✅	4
Multi-Agent Routing Value Iteration Network	❌	✅	✅	✅	❌	❌	✅	4
Multi-Objective Molecule Generation using Interpretable Substructures	✅	✅	✅	✅	❌	❌	✅	5
Multi-Precision Policy Enforced Training (MuPPET) : A Precision-Switching Strategy for Quantised Fixed-Point Training of CNNs	❌	✅	✅	✅	✅	❌	✅	5
Multi-Task Learning with User Preferences: Gradient Descent with Controlled Ascent in Pareto Optimization	✅	✅	✅	✅	❌	❌	✅	5
Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its Parallelization	✅	❌	✅	❌	❌	❌	✅	3
Multi-objective Bayesian Optimization using Pareto-frontier Entropy	❌	❌	❌	❌	❌	❌	✅	1
Multi-step Greedy Reinforcement Learning Algorithms	✅	❌	✅	❌	❌	❌	✅	3
Multiclass Neural Network Minimization via Tropical Newton Polytope Approximation	✅	✅	✅	❌	✅	❌	✅	5
Multidimensional Shape Constraints	❌	✅	✅	✅	❌	✅	✅	5
Multigrid Neural Memory	❌	❌	✅	❌	❌	❌	✅	2
Multilinear Latent Conditioning for Generating Unseen Attribute Combinations	❌	❌	✅	✅	❌	✅	✅	4
Multinomial Logit Bandit with Low Switching Cost	✅	❌	❌	❌	❌	❌	❌	1
Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis	✅	✅	✅	✅	❌	❌	✅	5
Mutual Transfer Learning for Massive Data	❌	❌	✅	✅	❌	❌	✅	3
My Fair Bandit: Distributed Learning of Max-Min Fairness with Multi-player Bandits	✅	❌	❌	❌	❌	❌	✅	2
NADS: Neural Architecture Distribution Search for Uncertainty Awareness	❌	❌	✅	❌	✅	❌	✅	3
NGBoost: Natural Gradient Boosting for Probabilistic Prediction	✅	✅	✅	✅	❌	❌	✅	5
Naive Exploration is Optimal for Online LQR	✅	❌	❌	❌	❌	❌	❌	1
Near Input Sparsity Time Kernel Embeddings via Adaptive Sampling	✅	❌	✅	✅	❌	❌	✅	4
Near-Tight Margin-Based Generalization Bounds for Support Vector Machines	❌	❌	❌	❌	❌	❌	❌	0
Near-linear time Gaussian process optimization with adaptive batching and resparsification	✅	✅	✅	❌	❌	❌	✅	4
Near-optimal Regret Bounds for Stochastic Shortest Path	✅	❌	❌	❌	❌	❌	❌	1
Near-optimal sample complexity bounds for learning Latent $k-$polytopes and applications to Ad-Mixtures	❌	❌	❌	❌	❌	❌	❌	0
Nearly Linear Row Sampling Algorithm for Quantile Regression	✅	❌	✅	❌	✅	✅	✅	5
Negative Sampling in Semi-Supervised learning	✅	❌	✅	✅	❌	❌	✅	4
Nested Subspace Arrangement for Representation of Relational Data	✅	✅	✅	✅	❌	✅	✅	6
NetGAN without GAN: From Random Walks to Low-Rank Approximations	✅	✅	✅	✅	❌	❌	✅	5
Neural Architecture Search in A Proxy Validation Loss Landscape	✅	❌	✅	✅	❌	❌	✅	4
Neural Clustering Processes	✅	✅	✅	❌	❌	❌	❌	3
Neural Contextual Bandits with UCB-based Exploration	✅	❌	✅	❌	❌	❌	✅	3
Neural Datalog Through Time: Informed Temporal Modeling via Logical Specification	❌	✅	✅	❌	✅	❌	✅	4
Neural Kernels Without Tangents	✅	❌	✅	✅	✅	❌	✅	5
Neural Network Control Policy Verification With Persistent Adversarial Perturbation	✅	❌	✅	❌	❌	❌	✅	3
Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks	❌	❌	✅	❌	❌	❌	✅	2
Neural Topic Modeling with Continual Lifelong Learning	✅	✅	✅	❌	✅	❌	✅	5
Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"	✅	✅	✅	✅	❌	❌	✅	5
New Oracle-Efficient Algorithms for Private Synthetic Data Release	✅	✅	✅	❌	✅	❌	✅	5
No-Regret Exploration in Goal-Oriented Reinforcement Learning	✅	❌	❌	❌	❌	❌	✅	2
No-Regret and Incentive-Compatible Online Learning	✅	✅	✅	❌	❌	❌	✅	4
Non-Autoregressive Neural Text-to-Speech	❌	❌	❌	❌	✅	❌	✅	2
Non-Stationary Delayed Bandits with Intermediate Observations	✅	❌	❌	❌	❌	❌	✅	2
Non-autoregressive Machine Translation with Disentangled Context Transformer	✅	✅	✅	✅	✅	✅	✅	7
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC	✅	❌	✅	✅	❌	❌	✅	4
Non-separable Non-stationary random fields	❌	✅	✅	✅	❌	❌	✅	4
Nonparametric Score Estimators	✅	✅	✅	❌	✅	❌	✅	5
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis	❌	❌	✅	❌	❌	❌	✅	2
Normalized Loss Functions for Deep Learning with Noisy Labels	❌	❌	✅	✅	❌	❌	✅	3
Normalizing Flows on Tori and Spheres	❌	❌	❌	❌	❌	❌	✅	1
OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning	✅	❌	❌	❌	❌	❌	✅	2
Obtaining Adjustable Regularization for Free via Iterate Averaging	❌	✅	✅	❌	✅	❌	✅	4
Off-Policy Actor-Critic with Shared Experience Replay	❌	❌	✅	❌	❌	❌	✅	2
On Approximate Thompson Sampling with Langevin Algorithms	✅	❌	❌	❌	❌	❌	✅	2
On Breaking Deep Generative Model-based Defenses and Beyond	✅	✅	✅	❌	❌	❌	✅	4
On Conditional Versus Marginal Bias in Multi-Armed Bandits	❌	❌	❌	❌	❌	❌	✅	1
On Contrastive Learning for Likelihood-free Inference	✅	✅	❌	✅	❌	❌	✅	4
On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent	✅	❌	✅	❌	❌	❌	✅	3
On Coresets for Regularized Regression	❌	✅	✅	❌	✅	✅	✅	5
On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data	✅	✅	✅	❌	❌	❌	✅	4
On Efficient Constructions of Checkpoints	✅	❌	✅	❌	✅	❌	✅	4
On Efficient Low Distortion Ultrametric Embedding	❌	❌	✅	❌	❌	❌	✅	2
On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems	✅	❌	✅	❌	❌	❌	✅	3
On Implicit Regularization in $β$-VAEs	❌	❌	✅	✅	❌	❌	✅	3
On Layer Normalization in the Transformer Architecture	❌	❌	✅	✅	❌	❌	✅	3
On Learning Language-Invariant Representations for Universal Machine Translation	❌	❌	❌	❌	❌	❌	❌	0
On Learning Sets of Symmetric Elements	❌	❌	✅	❌	✅	❌	❌	2
On Leveraging Pretrained GANs for Generation with Limited Data	❌	✅	✅	❌	✅	❌	✅	4
On Lp-norm Robustness of Ensemble Decision Stumps and Trees	❌	✅	✅	❌	✅	❌	✅	4
On Relativistic f-Divergences	❌	✅	✅	❌	❌	❌	✅	3
On Second-Order Group Influence Functions for Black-Box Predictions	❌	❌	✅	❌	❌	❌	✅	2
On Semi-parametric Inference for BART	❌	❌	❌	❌	❌	❌	❌	0
On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm	✅	❌	✅	❌	❌	❌	✅	3
On Validation and Planning of An Optimal Decision Rule with Application in Healthcare Studies	❌	✅	✅	✅	❌	❌	✅	4
On Variational Learning of Controllable Representations for Text without Supervision	❌	✅	✅	✅	❌	❌	✅	4
On a projective ensemble approach to two sample test for equality of distributions	❌	❌	✅	❌	✅	✅	✅	4
On hyperparameter tuning in general clustering problemsm	✅	❌	✅	✅	✅	❌	✅	5
On the (In)tractability of Computing Normalizing Constants for the Product of Determinantal Point Processes	❌	❌	❌	❌	❌	❌	❌	0
On the Convergence of Nesterov’s Accelerated Gradient Method in Stochastic Settings	❌	❌	❌	❌	❌	❌	✅	1
On the Expressivity of Neural Networks for Deep Reinforcement Learning	✅	❌	✅	❌	❌	❌	❌	2
On the Generalization Benefit of Noise in Stochastic Gradient Descent	❌	❌	✅	❌	❌	❌	✅	2
On the Generalization Effects of Linear Transformations in Data Augmentation	✅	❌	✅	✅	❌	❌	✅	4
On the Global Convergence Rates of Softmax Policy Gradient Methods	✅	❌	❌	❌	❌	❌	✅	2
On the Global Optimality of Model-Agnostic Meta-Learning	✅	❌	❌	❌	❌	❌	❌	1
On the Iteration Complexity of Hypergradient Computation	✅	✅	✅	✅	❌	❌	✅	5
On the Noisy Gradient Descent that Generalizes as SGD	✅	✅	✅	❌	❌	❌	❌	3
On the Number of Linear Regions of Convolutional Neural Networks	❌	✅	❌	❌	❌	❌	✅	2
On the Power of Compressed Sensing with Generative Models	❌	❌	❌	❌	❌	❌	❌	0
On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation	❌	❌	✅	❌	❌	❌	✅	2
On the Sample Complexity of Adversarial Multi-Source PAC Learning	✅	❌	❌	❌	❌	❌	❌	1
On the Theoretical Properties of the Network Jackknife	❌	❌	✅	❌	❌	❌	✅	2
On the Unreasonable Effectiveness of the Greedy Algorithm: Greedy Adapts to Sharpness	✅	❌	✅	❌	❌	❌	✅	3
On the consistency of top-k surrogate losses	❌	❌	❌	❌	✅	❌	✅	2
One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control	✅	❌	✅	✅	❌	❌	✅	4
One Size Fits All: Can We Train One Denoiser for All Noise Levels?	❌	❌	✅	✅	❌	❌	✅	3
One-shot Distributed Ridge Regression in High Dimensions	✅	❌	✅	✅	❌	❌	✅	4
Online Bayesian Moment Matching based SAT Solver Heuristics	❌	✅	✅	❌	✅	✅	✅	5
Online Continual Learning from Imbalanced Data	✅	❌	✅	❌	✅	❌	✅	4
Online Control of the False Coverage Rate and False Sign Rate	✅	❌	❌	❌	❌	❌	✅	2
Online Convex Optimization in the Random Order Model	✅	❌	✅	❌	❌	❌	✅	3
Online Dense Subgraph Discovery via Blurred-Graph Feedback	✅	❌	✅	❌	✅	✅	✅	5
Online Learned Continual Compression with Adaptive Quantization Modules	✅	❌	✅	✅	❌	❌	❌	3
Online Learning for Active Cache Synchronization	✅	✅	❌	❌	✅	❌	✅	4
Online Learning with Dependent Stochastic Feedback Graphs	✅	❌	✅	❌	❌	❌	✅	3
Online Learning with Imperfect Hints	✅	❌	❌	❌	❌	❌	❌	1
Online Multi-Kernel Learning with Graph-Structured Feedback	✅	❌	✅	❌	❌	❌	✅	3
Online Pricing with Offline Data: Phase Transition and Inverse Square Law	✅	❌	❌	❌	❌	❌	❌	1
Online metric algorithms with untrusted predictions	✅	✅	✅	❌	❌	❌	✅	4
Online mirror descent and dual averaging: keeping pace in the dynamic case	✅	❌	❌	❌	❌	❌	❌	1
Operation-Aware Soft Channel Pruning using Differentiable Masks	❌	❌	✅	✅	✅	❌	✅	4
Optimal Bounds between f-Divergences and Integral Probability Metrics	❌	❌	❌	❌	❌	❌	❌	0
Optimal Continual Learning has Perfect Memory and is NP-hard	❌	❌	❌	❌	❌	❌	❌	0
Optimal Differential Privacy Composition for Exponential Mechanisms	❌	❌	❌	❌	❌	❌	❌	0
Optimal Estimator for Unlabeled Linear Regression	✅	❌	❌	❌	❌	❌	✅	2
Optimal Non-parametric Learning in Repeated Contextual Auctions with Strategic Buyer	✅	❌	❌	❌	❌	❌	❌	1
Optimal Randomized First-Order Methods for Least-Squares Problems	✅	❌	✅	❌	❌	❌	✅	3
Optimal Robust Learning of Discrete Distributions from Batches	✅	✅	❌	❌	✅	❌	✅	4
Optimal Sequential Maximization: One Interview is Enough!	✅	❌	❌	❌	❌	❌	✅	2
Optimal approximation for unconstrained non-submodular minimization	❌	✅	✅	❌	✅	❌	✅	4
Optimal transport mapping via input convex neural networks	✅	✅	✅	❌	❌	❌	✅	4
Optimally Solving Two-Agent Decentralized POMDPs Under One-Sided Information Sharing	✅	✅	❌	❌	✅	❌	✅	4
Optimistic Bounds for Multi-output Learning	❌	❌	❌	❌	❌	❌	❌	0
Optimistic Policy Optimization with Bandit Feedback	✅	❌	❌	❌	❌	❌	❌	1
Optimization Theory for ReLU Neural Networks Trained with Normalization Layers	❌	❌	❌	❌	❌	❌	✅	1
Optimization and Analysis of the pAp@k Metric for Recommender Systems	✅	✅	✅	❌	❌	❌	✅	4
Optimization from Structured Samples for Coverage Functions	✅	❌	❌	❌	❌	❌	❌	1
Optimizer Benchmarking Needs to Account for Hyperparameter Tuning	✅	❌	✅	✅	❌	❌	✅	4
Optimizing Black-box Metrics with Adaptive Surrogates	✅	✅	✅	✅	❌	❌	✅	5
Optimizing Data Usage via Differentiable Rewards	✅	❌	✅	✅	❌	❌	✅	4
Optimizing Dynamic Structures with Bayesian Generative Search	✅	❌	✅	✅	❌	❌	✅	4
Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach	❌	✅	✅	❌	❌	❌	✅	3
Optimizing for the Future in Non-Stationary MDPs	✅	✅	✅	❌	❌	❌	✅	4
Option Discovery in the Absence of Rewards with Manifold Analysis	✅	❌	✅	❌	❌	❌	✅	3
Oracle Efficient Private Non-Convex Optimization	✅	❌	✅	❌	❌	❌	✅	3
Ordinal Non-negative Matrix Factorization for Recommendation	✅	✅	✅	❌	✅	❌	✅	5
Orthogonalized SGD and Nested Architectures for Anytime Neural Networks	✅	❌	✅	❌	❌	❌	✅	3
Overfitting in adversarially robust deep learning	❌	✅	✅	✅	✅	❌	✅	5
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions	❌	❌	✅	✅	❌	❌	✅	3
PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization	✅	✅	✅	✅	❌	❌	✅	5
PENNI: Pruned Kernel Sharing for Efficient CNN Inference	❌	✅	✅	✅	✅	✅	✅	6
PackIt: A Virtual Environment for Geometric Planning	✅	✅	✅	✅	✅	❌	✅	6
Parallel Algorithm for Non-Monotone DR-Submodular Maximization	✅	✅	❌	❌	✅	❌	✅	4
Parameter-free, Dynamic, and Strongly-Adaptive Online Learning	✅	❌	❌	❌	❌	❌	❌	1
Parameterized Rate-Distortion Stochastic Encoder	✅	✅	✅	✅	❌	❌	✅	5
Parametric Gaussian Process Regressors	✅	✅	✅	✅	❌	❌	✅	5
Partial Trace Regression and Low-Rank Kraus Decomposition	❌	✅	✅	❌	❌	❌	✅	3
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates	❌	✅	✅	❌	❌	❌	❌	2
Perceptual Generative Autoencoders	❌	✅	✅	❌	❌	❌	✅	3
Performative Prediction	✅	❌	✅	❌	❌	❌	✅	3
Piecewise Linear Regression via a Difference of Convex Functions	✅	✅	✅	✅	❌	❌	✅	5
Planning to Explore via Self-Supervised World Models	✅	✅	✅	❌	❌	❌	✅	4
PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination	❌	✅	✅	✅	✅	❌	✅	5
Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates	✅	✅	✅	❌	✅	❌	✅	5
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning	❌	✅	❌	❌	❌	❌	✅	2
PolyGen: An Autoregressive Generative Model of 3D Meshes	❌	❌	✅	✅	✅	❌	✅	4
Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix	✅	✅	✅	✅	❌	❌	✅	5
Population-Based Black-Box Optimization for Biological Sequence Design	✅	❌	✅	❌	❌	❌	✅	3
PowerNorm: Rethinking Batch Normalization in Transformers	✅	✅	✅	✅	❌	❌	✅	5
Predicting Choice with Set-Dependent Aggregation	❌	❌	✅	✅	❌	❌	✅	3
Predicting deliberative outcomes	❌	❌	✅	❌	❌	❌	✅	2
Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control	✅	✅	❌	❌	❌	❌	✅	3
Predictive Coding for Locally-Linear Control	❌	✅	❌	❌	❌	❌	✅	2
Predictive Multiplicity in Classification	✅	✅	✅	❌	✅	❌	✅	5
Predictive Sampling with Forecasting Autoregressive Models	✅	❌	✅	✅	✅	✅	✅	6
Preference Modeling with Context-Dependent Salient Features	❌	❌	✅	✅	❌	❌	✅	3
Preselection Bandits	✅	❌	❌	❌	❌	❌	✅	2
Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification	❌	✅	✅	✅	❌	❌	✅	4
Principled learning method for Wasserstein distributionally robust optimization with local perturbations	❌	✅	✅	❌	❌	❌	❌	2
Private Counting from Anonymous Messages: Near-Optimal Accuracy with Vanishing Communication Overhead	✅	❌	✅	❌	❌	❌	❌	2
Private Outsourced Bayesian Optimization	✅	❌	✅	❌	❌	❌	✅	3
Private Query Release Assisted by Public Data	✅	❌	❌	❌	❌	❌	❌	1
Private Reinforcement Learning with PAC and Regret Guarantees	✅	❌	❌	❌	❌	❌	❌	1
Privately Learning Markov Random Fields	✅	❌	❌	❌	❌	❌	❌	1
Privately detecting changes in unknown distributions	✅	❌	✅	❌	❌	❌	✅	3
Probing Emergent Semantics in Predictive Agents via Question Answering	❌	❌	❌	❌	❌	❌	✅	1
Problems with Shapley-value-based explanations as feature importance measures	❌	❌	❌	❌	❌	❌	❌	0
Progressive Graph Learning for Open-Set Domain Adaptation	❌	❌	✅	✅	❌	❌	✅	3
Progressive Identification of True Labels for Partial-Label Learning	✅	✅	✅	❌	✅	❌	✅	5
Projection-free Distributed Online Convex Optimization with $O(\sqrtT)$ Communication Complexity	✅	❌	✅	❌	❌	❌	✅	3
Projective Preferential Bayesian Optimization	✅	✅	✅	❌	✅	❌	✅	5
Proper Network Interpretability Helps Adversarial Robustness in Classification	❌	✅	✅	❌	✅	❌	✅	4
Provable Representation Learning for Imitation Learning via Bi-level Optimization	❌	❌	❌	❌	✅	❌	✅	2
Provable Self-Play Algorithms for Competitive Reinforcement Learning	✅	❌	❌	❌	❌	❌	❌	1
Provable Smoothness Guarantees for Black-Box Variational Inference	❌	❌	❌	❌	❌	❌	✅	1
Provable guarantees for decision tree induction: the agnostic setting	✅	❌	❌	❌	❌	❌	❌	1
Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation	✅	✅	✅	❌	❌	❌	✅	4
Provably Efficient Exploration in Policy Optimization	✅	❌	❌	❌	❌	❌	❌	1
Provably Efficient Model-based Policy Adaptation	✅	✅	✅	❌	❌	❌	✅	4
Proving the Lottery Ticket Hypothesis: Pruning is All You Need	❌	❌	❌	❌	❌	❌	❌	0
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup	✅	✅	✅	❌	❌	❌	✅	4
Q-value Path Decomposition for Deep Multiagent Reinforcement Learning	✅	❌	✅	❌	❌	❌	✅	3
Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraints	✅	❌	✅	❌	✅	❌	✅	4
Quantized Decentralized Stochastic Learning over Directed Graphs	✅	❌	✅	❌	❌	❌	✅	3
Quantum Boosting	✅	❌	❌	❌	❌	❌	❌	1
Quantum Expectation-Maximization for Gaussian mixture models	✅	❌	✅	❌	❌	❌	✅	3
R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games	✅	❌	✅	❌	❌	❌	✅	3
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr	✅	❌	✅	✅	❌	❌	✅	4
ROMA: Multi-Agent Reinforcement Learning with Emergent Roles	❌	✅	✅	❌	❌	❌	✅	3
Radioactive data: tracing through training	❌	❌	✅	❌	❌	❌	✅	2
Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization	✅	❌	✅	❌	❌	❌	✅	3
Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures	❌	❌	✅	✅	❌	❌	✅	3
Random extrapolation for primal-dual coordinate descent	✅	❌	✅	❌	❌	❌	✅	3
Randomization matters How to defend against strong adversarial attacks	✅	❌	✅	❌	❌	❌	✅	3
Randomized Block-Diagonal Preconditioning for Parallel Learning	✅	❌	✅	❌	❌	❌	✅	3
Randomized Smoothing of All Shapes and Sizes	✅	✅	✅	❌	❌	❌	✅	4
Randomly Projected Additive Gaussian Processes for Regression	❌	✅	✅	❌	✅	❌	✅	4
Rank Aggregation from Pairwise Comparisons in the Presence of Adversarial Corruptions	✅	❌	❌	❌	❌	❌	✅	2
Rate-distortion optimization guided autoencoder for isometric embedding in Euclidean latent space	❌	❌	✅	❌	❌	❌	✅	2
Ready Policy One: World Building Through Active Learning	✅	✅	✅	❌	❌	❌	❌	3
Real-Time Optimisation for Online Learning in Auctions	✅	❌	❌	❌	❌	❌	✅	2
Recht-Re Noncommutative Arithmetic-Geometric Mean Conjecture is False	❌	✅	❌	❌	✅	✅	✅	4
Recovery of Sparse Signals from a Mixture of Linear Samples	✅	❌	❌	❌	❌	❌	❌	1
Recurrent Hierarchical Topic-Guided RNN for Language Generation	✅	✅	✅	✅	✅	❌	✅	6
Reducing Sampling Error in Batch Temporal Difference Learning	✅	❌	❌	✅	❌	❌	✅	3
Refined bounds for algorithm configuration: The knife-edge of dual class approximability	✅	❌	✅	✅	✅	✅	✅	6
Regularized Optimal Transport is Ground Cost Adversarial	✅	❌	❌	❌	❌	❌	❌	1
Reinforcement Learning for Integer Programming: Learning to Cut	✅	❌	❌	❌	❌	✅	✅	3
Reinforcement Learning for Molecular Design Guided by Quantum Mechanics	❌	✅	✅	❌	✅	✅	❌	4
Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism	✅	❌	❌	❌	❌	❌	❌	1
Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound	✅	❌	❌	❌	❌	❌	❌	1
Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows	✅	✅	✅	❌	❌	❌	❌	3
Reliable Fidelity and Diversity Metrics for Generative Models	❌	✅	✅	❌	❌	❌	✅	3
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks	✅	✅	✅	✅	❌	❌	✅	5
Representation Learning via Adversarially-Contrastive Optimal Transport	❌	❌	✅	✅	❌	❌	✅	3
Representations for Stable Off-Policy Reinforcement Learning	❌	❌	✅	✅	❌	❌	✅	3
Representing Unordered Data Using Complex-Weighted Multiset Automata	❌	✅	❌	✅	❌	❌	✅	3
Reserve Pricing in Repeated Second-Price Auctions with Strategic Bidders	✅	❌	❌	❌	❌	❌	❌	1
Responsive Safety in Reinforcement Learning by PID Lagrangian Methods	✅	✅	✅	❌	❌	❌	✅	4
Restarted Bayesian Online Change-point Detector achieves Optimal Detection Delay	✅	✅	✅	❌	❌	❌	✅	4
Rethinking Bias-Variance Trade-off for Generalization of Neural Networks	✅	✅	✅	❌	❌	❌	✅	4
Retrieval Augmented Language Model Pre-Training	❌	❌	✅	✅	✅	❌	✅	4
Retro: Learning Retrosynthetic Planning with Neural Guided A Search	✅	✅	✅	✅	❌	❌	✅	5
Reverse-engineering deep ReLU networks	✅	❌	✅	❌	❌	❌	✅	3
Revisiting Fundamentals of Experience Replay	❌	❌	✅	❌	❌	❌	✅	2
Revisiting Spatial Invariance with Low-Rank Local Connectivity	✅	✅	✅	✅	✅	❌	✅	6
Revisiting Training Strategies and Generalization Performance in Deep Metric Learning	❌	✅	✅	❌	✅	❌	✅	4
Reward-Free Exploration for Reinforcement Learning	✅	❌	❌	❌	❌	❌	❌	1
Rigging the Lottery: Making All Tickets Winners	✅	✅	✅	❌	❌	❌	✅	4
Robust Bayesian Classification Using An Optimistic Score Ratio	✅	✅	✅	✅	✅	❌	✅	6
Robust Graph Representation Learning via Neural Sparsification	✅	❌	✅	✅	❌	❌	✅	4
Robust Learning with the Hilbert-Schmidt Independence Criterion	✅	✅	✅	✅	❌	❌	✅	5
Robust One-Bit Recovery via ReLU Generative Networks: Near-Optimal Statistical Rate and Global Landscape Analysis	❌	❌	❌	❌	❌	❌	❌	0
Robust Outlier Arm Identification	✅	✅	✅	❌	❌	❌	✅	4
Robust Pricing in Dynamic Mechanism Design	❌	❌	❌	❌	❌	❌	❌	0
Robust and Stable Black Box Explanations	❌	❌	✅	❌	❌	❌	✅	2
Robustifying Sequential Neural Processes	✅	❌	✅	❌	❌	❌	✅	3
Robustness to Programmable String Transformations via Augmented Abstract Training	✅	✅	✅	✅	❌	❌	✅	5
Robustness to Spurious Correlations via Human Annotations	❌	✅	✅	✅	❌	❌	❌	3
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning	✅	❌	✅	❌	❌	❌	✅	3
SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates	✅	❌	✅	❌	❌	❌	❌	2
SGD Learns One-Layer Networks in WGANs	✅	❌	❌	❌	❌	❌	✅	2
SIGUA: Forgetting May Make Learning with Noisy Labels More Robust	✅	❌	✅	❌	❌	❌	✅	3
Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data	✅	✅	✅	❌	❌	❌	✅	4
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences	✅	✅	✅	❌	✅	❌	✅	5
Safe Reinforcement Learning in Constrained Markov Decision Processes	✅	✅	❌	❌	❌	❌	✅	3
Safe screening rules for L0-regression from Perspective Relaxations	❌	❌	✅	❌	✅	✅	✅	4
Sample Amplification: Increasing Dataset Size even when Learning is Impossible	✅	❌	❌	❌	❌	❌	✅	2
Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative Priors	❌	❌	✅	❌	❌	❌	✅	2
Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning	❌	✅	✅	❌	✅	❌	✅	4
Scalable Deep Generative Modeling for Sparse Graphs	✅	✅	✅	❌	❌	❌	✅	4
Scalable Differentiable Physics for Learning and Control	❌	✅	❌	❌	✅	✅	✅	4
Scalable Differential Privacy with Certified Robustness in Adversarial Learning	✅	✅	✅	❌	❌	❌	✅	4
Scalable Exact Inference in Multi-Output Gaussian Processes	✅	✅	✅	❌	✅	❌	✅	5
Scalable Gaussian Process Separation for Kernels with a Non-Stationary Phase	❌	✅	✅	❌	✅	✅	✅	5
Scalable Identification of Partially Observed Systems with Certainty-Equivalent EM	✅	✅	✅	✅	✅	❌	✅	6
Scalable Nearest Neighbor Search for Optimal Transport	❌	✅	✅	❌	✅	❌	❌	3
Scalable and Efficient Comparison-based Search without Features	✅	❌	✅	❌	❌	❌	✅	3
Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing	✅	✅	❌	❌	❌	❌	✅	3
Schatten Norms in Matrix Streams: Hello Sparsity, Goodbye Dimension	❌	❌	✅	❌	❌	❌	❌	1
Searching to Exploit Memorization Effect in Learning with Noisy Labels	✅	❌	✅	✅	✅	✅	✅	6
Second-Order Provable Defenses against Adversarial Attacks	❌	❌	✅	❌	✅	❌	✅	3
Selective Dyna-Style Planning Under Limited Model Capacity	❌	❌	❌	❌	❌	❌	❌	0
Self-Attentive Associative Memory	❌	✅	✅	❌	❌	❌	✅	3
Self-Attentive Hawkes Process	❌	✅	✅	✅	✅	❌	✅	5
Self-Concordant Analysis of Frank-Wolfe Algorithms	✅	✅	✅	❌	✅	✅	❌	5
Self-Modulating Nonparametric Event-Tensor Factorization	❌	❌	✅	❌	❌	❌	✅	2
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training	❌	✅	✅	✅	❌	❌	✅	4
Self-supervised Label Augmentation via Input Transformations	✅	✅	✅	❌	❌	❌	✅	4
Semi-Supervised Learning with Normalizing Flows	❌	✅	✅	✅	❌	❌	✅	4
Semi-Supervised StyleGAN for Disentanglement Learning	❌	❌	✅	❌	❌	❌	✅	2
Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees	❌	❌	✅	❌	❌	❌	✅	2
Semismooth Newton Algorithm for Efficient Projections onto $\ell_1, ∞$-norm Ball	✅	✅	✅	❌	✅	❌	✅	5
Sequence Generation with Mixed Representations	❌	✅	✅	✅	❌	❌	✅	4
Sequential Cooperative Bayesian Inference	✅	❌	❌	❌	❌	❌	✅	2
Sequential Transfer in Reinforcement Learning with a Generative Model	✅	❌	✅	❌	❌	❌	✅	3
Set Functions for Time Series	❌	✅	✅	✅	❌	❌	✅	4
Sets Clustering	✅	✅	✅	❌	✅	✅	❌	5
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion	❌	✅	❌	❌	✅	❌	✅	3
Sharp Statistical Guaratees for Adversarially Robust Gaussian Classification	✅	❌	❌	❌	❌	❌	✅	2
SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification	❌	✅	✅	❌	❌	❌	✅	3
Simple and Deep Graph Convolutional Networks	❌	❌	✅	✅	❌	❌	✅	3
Simple and sharp analysis of k-means\|\|	✅	❌	❌	❌	❌	❌	❌	1
Simultaneous Inference for Massive Data: Distributed Bootstrap	✅	❌	❌	❌	❌	❌	✅	2
Single Point Transductive Prediction	❌	✅	✅	✅	❌	❌	✅	4
Skew-Fit: State-Covering Self-Supervised Reinforcement Learning	✅	❌	✅	❌	❌	❌	✅	3
Small Data, Big Decisions: Model Selection in the Small-Data Regime	❌	❌	✅	✅	❌	❌	✅	3
Small-GAN: Speeding up GAN Training using Core-Sets	✅	❌	✅	❌	✅	❌	✅	4
Smaller, more accurate regression forests using tree alternating optimization	✅	❌	✅	❌	❌	❌	✅	3
Soft Threshold Weight Reparameterization for Learnable Sparsity	✅	✅	✅	✅	✅	❌	✅	6
SoftSort: A Continuous Relaxation for the argsort Operator	✅	✅	✅	✅	❌	❌	✅	5
Source Separation with Deep Generative Priors	✅	✅	✅	❌	❌	❌	✅	4
Sparse Convex Optimization via Adaptively Regularized Hard Thresholding	✅	❌	✅	❌	❌	❌	❌	2
Sparse Gaussian Processes with Spherical Harmonic Features	❌	❌	✅	✅	✅	❌	✅	4
Sparse Shrunk Additive Models	❌	❌	✅	✅	❌	❌	✅	3
Sparse Sinkhorn Attention	❌	❌	✅	❌	✅	❌	✅	3
Sparse Subspace Clustering with Entropy-Norm	❌	❌	✅	❌	✅	❌	✅	3
Sparsified Linear Programming for Zero-Sum Equilibrium Finding	✅	❌	✅	❌	❌	✅	✅	4
Spectral Clustering with Graph Neural Networks for Graph Pooling	❌	✅	✅	✅	❌	❌	❌	3
Spectral Frank-Wolfe Algorithm: Strict Complementarity and Linear Convergence	✅	❌	❌	❌	❌	❌	✅	2
Spectral Graph Matching and Regularized Quadratic Relaxations: Algorithm and Theory	✅	❌	✅	❌	❌	❌	✅	3
Spectral Subsampling MCMC for Stationary Time Series	❌	❌	✅	❌	❌	❌	✅	2
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks	✅	✅	✅	❌	❌	❌	✅	4
Spread Divergence	❌	❌	✅	❌	❌	❌	✅	2
Stabilizing Differentiable Architecture Search via Perturbation-based Regularization	✅	✅	✅	✅	✅	❌	✅	6
Stabilizing Transformers for Reinforcement Learning	❌	❌	✅	❌	❌	❌	✅	2
State Space Expectation Propagation: Efficient Inference Schemes for Temporal Gaussian Processes	✅	✅	✅	✅	✅	❌	✅	6
Statistically Efficient Off-Policy Policy Gradients	✅	❌	❌	❌	❌	❌	✅	2
Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization	✅	✅	✅	❌	❌	❌	✅	4
Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Differential Equations with Variational Wishart Diffusions	❌	✅	✅	✅	❌	❌	✅	4
Stochastic Flows and Geometric Optimization on the Orthogonal Group	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization	✅	✅	✅	❌	❌	❌	✅	4
Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Gradient and Langevin Processes	❌	❌	✅	✅	❌	❌	✅	3
Stochastic Hamiltonian Gradient Methods for Smooth Games	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Latent Residual Video Prediction	❌	✅	✅	❌	❌	❌	❌	2
Stochastic Optimization for Non-convex Inf-Projection Problems	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Optimization for Regularized Wasserstein Estimators	✅	❌	❌	❌	❌	❌	✅	2
Stochastic Regret Minimization in Extensive-Form Games	✅	❌	❌	❌	❌	❌	✅	2
Stochastic Subspace Cubic Newton Method	✅	❌	✅	❌	❌	❌	❌	2
Stochastic bandits with arm-dependent delays	✅	❌	❌	❌	❌	❌	✅	2
StochasticRank: Global Optimization of Scale-Free Discrete Functions	❌	✅	✅	✅	❌	❌	✅	4
Stochastically Dominant Distributional Reinforcement Learning	✅	❌	✅	❌	❌	❌	❌	2
Strategic Classification is Causal Modeling in Disguise	❌	❌	❌	❌	❌	❌	❌	0
Strategyproof Mean Estimation from Multiple-Choice Questions	❌	❌	❌	❌	❌	❌	❌	0
Streaming Coresets for Symmetric Tensor Factorization	✅	❌	❌	❌	❌	❌	✅	2
Streaming Submodular Maximization under a k-Set System Constraint	✅	❌	✅	❌	❌	❌	✅	3
Streaming k-Submodular Maximization under Noise subject to Size Constraint	✅	✅	✅	❌	❌	❌	✅	4
Strength from Weakness: Fast Learning Using Weak Supervision	✅	❌	✅	❌	❌	❌	❌	2
Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling	✅	✅	✅	❌	❌	❌	✅	4
Stronger and Faster Wasserstein Adversarial Attacks	✅	✅	✅	✅	✅	❌	✅	6
Structural Language Models of Code	❌	✅	✅	✅	✅	❌	✅	5
Structure Adaptive Algorithms for Stochastic Bandits	✅	❌	❌	❌	❌	❌	❌	1
Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis	✅	❌	❌	❌	❌	❌	❌	1
Structured Policy Iteration for Linear Quadratic Regulator	✅	❌	✅	❌	✅	❌	✅	4
Structured Prediction with Partial Labelling through the Infimum Loss	❌	✅	✅	❌	❌	❌	❌	2
Student Specialization in Deep Rectified Networks With Finite Width and Input Dimension	❌	✅	✅	❌	❌	❌	✅	3
Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location	✅	❌	✅	✅	❌	❌	✅	4
Sub-Goal Trees a Framework for Goal-Based Reinforcement Learning	✅	✅	❌	❌	❌	❌	✅	3
Sub-linear Memory Sketches for Near Neighbor Search on Streaming Data	✅	❌	✅	❌	❌	❌	✅	3
Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization Errors	✅	❌	❌	❌	❌	❌	❌	1
Super-efficiency of automatic differentiation for functions defined as a minimum	❌	✅	❌	❌	❌	❌	❌	1
Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent	❌	❌	✅	❌	❌	❌	✅	2
Supervised Quantile Normalization for Low Rank Matrix Factorization	✅	❌	✅	❌	❌	❌	✅	3
Supervised learning: no loss no cry	✅	❌	✅	❌	❌	❌	✅	3
Symbolic Network: Generalized Neural Policies for Relational MDPs	❌	✅	✅	❌	✅	❌	✅	4
T-Basis: a Compact Representation for Neural Networks	❌	✅	✅	✅	❌	❌	✅	4
T-GD: Transferable GAN-generated Images Detection Framework	✅	✅	✅	✅	❌	❌	✅	5
Tails of Lipschitz Triangular Flows	❌	❌	✅	✅	✅	❌	✅	4
Task Understanding from Confusing Multi-task Data	❌	❌	✅	❌	❌	❌	✅	2
Task-Oriented Active Perception and Planning in Environments with Partially Known Semantics	✅	✅	❌	❌	❌	❌	✅	3
TaskNorm: Rethinking Batch Normalization for Meta-Learning	❌	✅	✅	❌	❌	❌	❌	2
Taylor Expansion Policy Optimization	✅	❌	✅	❌	❌	❌	✅	3
Teaching with Limited Information on the Learner’s Behaviour	✅	❌	✅	❌	❌	❌	❌	2
Temporal Logic Point Processes	❌	❌	✅	❌	❌	❌	✅	2
Temporal Phenotyping using Deep Predictive Clustering of Disease Progression	✅	✅	✅	✅	❌	❌	✅	5
Tensor denoising and completion based on ordinal observations	✅	✅	✅	✅	❌	❌	✅	5
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts	❌	✅	✅	❌	❌	❌	✅	3
The Boomerang Sampler	❌	✅	❌	❌	❌	❌	✅	2
The Buckley-Osthus model and the block preferential attachment model: statistical analysis and application	❌	❌	✅	❌	❌	❌	✅	2
The Complexity of Finding Stationary Points with Stochastic Gradient Descent	❌	❌	❌	❌	❌	❌	❌	0
The Cost-free Nature of Optimally Tuning Tikhonov Regularizers and Other Ordered Smoothers	❌	✅	❌	❌	❌	❌	✅	2
The Differentiable Cross-Entropy Method	✅	✅	✅	❌	❌	❌	✅	4
The Effect of Natural Distribution Shift on Question Answering Models	❌	❌	✅	✅	❌	❌	❌	2
The FAST Algorithm for Submodular Maximization	✅	✅	✅	❌	✅	❌	✅	5
The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent	❌	❌	✅	✅	❌	❌	✅	3
The Implicit Regularization of Stochastic Gradient Flow for Least Squares	❌	❌	❌	❌	❌	❌	✅	1
The Implicit and Explicit Regularization Effects of Dropout	✅	✅	✅	✅	❌	❌	✅	5
The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulation	❌	❌	❌	❌	❌	❌	✅	1
The Many Shapley Values for Model Explanation	✅	❌	✅	❌	❌	❌	❌	2
The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization	❌	❌	❌	❌	❌	❌	✅	1
The Non-IID Data Quagmire of Decentralized Machine Learning	✅	✅	✅	✅	❌	❌	✅	5
The Performance Analysis of Generalized Margin Maximizers on Separable Data	❌	❌	❌	❌	❌	❌	✅	1
The Role of Regularization in Classification of High-dimensional Noisy Gaussian Mixture	❌	❌	❌	❌	❌	❌	✅	1
The Sample Complexity of Best-$k$ Items Selection from Pairwise Comparisons	✅	✅	✅	❌	❌	❌	✅	4
The Shapley Taylor Interaction Index	❌	❌	✅	❌	❌	❌	✅	2
The Tree Ensemble Layer: Differentiability meets Conditional Computation	✅	✅	✅	✅	❌	✅	✅	6
The Usual Suspects? Reassessing Blame for VAE Posterior Collapse	❌	❌	✅	❌	❌	❌	✅	2
The continuous categorical: a novel simplex-valued exponential family	✅	✅	✅	❌	❌	❌	✅	4
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks	❌	✅	✅	✅	❌	❌	❌	3
Thompson Sampling Algorithms for Mean-Variance Bandits	✅	✅	✅	❌	❌	❌	✅	4
Thompson Sampling via Local Uncertainty	✅	✅	✅	❌	✅	✅	✅	6
Tight Bounds on Minimax Regret under Logarithmic Loss via Self-Concordance	❌	❌	❌	❌	❌	❌	❌	0
Tightening Exploration in Upper Confidence Reinforcement Learning	✅	✅	✅	❌	❌	❌	✅	4
Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders	❌	✅	✅	✅	❌	❌	❌	3
Time-Consistent Self-Supervision for Semi-Supervised Learning	✅	❌	✅	✅	❌	❌	✅	4
Time-aware Large Kernel Convolutions	❌	✅	✅	✅	✅	❌	✅	5
Too Relaxed to Be Fair	✅	✅	✅	✅	❌	❌	✅	5
Topic Modeling via Full Dependence Mixtures	✅	✅	✅	❌	❌	❌	✅	4
Topological Autoencoders	❌	✅	✅	✅	❌	❌	✅	4
Topologically Densified Distributions	❌	✅	✅	✅	❌	❌	✅	4
Towards Accurate Post-training Network Quantization via Bit-Split and Stitching	✅	✅	✅	✅	❌	❌	✅	5
Towards Adaptive Residual Network Training: A Neural-ODE Perspective	✅	✅	✅	✅	✅	❌	✅	6
Towards Non-Parametric Drift Detection via Dynamic Adapting Window Independence Drift Detection (DAWIDD)	✅	✅	✅	❌	❌	❌	❌	3
Towards Understanding the Dynamics of the First-Order Adversaries	❌	❌	✅	❌	❌	❌	❌	1
Towards Understanding the Regularization of Adversarial Robustness on Neural Networks	❌	❌	✅	❌	❌	❌	❌	1
Towards a General Theory of Infinite-Width Limits of Neural Classifiers	❌	❌	✅	❌	❌	❌	✅	2
Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers	❌	❌	✅	✅	✅	❌	✅	4
Training Binary Neural Networks through Learning with Noisy Supervision	✅	❌	✅	✅	✅	❌	✅	5
Training Binary Neural Networks using the Bayesian Learning Rule	✅	✅	✅	✅	❌	❌	✅	5
Training Deep Energy-Based Models with f-Divergence Minimization	✅	✅	✅	✅	❌	❌	✅	5
Training Linear Neural Networks: Non-Local Convergence and Complexity Results	❌	❌	❌	❌	❌	❌	✅	1
Training Neural Networks for and by Interpolation	✅	✅	✅	✅	❌	❌	✅	5
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics	❌	✅	✅	✅	❌	❌	✅	4
Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources	✅	✅	✅	✅	❌	❌	✅	5
Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time	❌	✅	✅	❌	❌	❌	✅	3
Transformer Hawkes Process	❌	✅	✅	❌	❌	❌	❌	2
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention	✅	✅	✅	❌	✅	❌	✅	5
Transparency Promotion with Model-Agnostic Linear Competitors	✅	❌	✅	✅	❌	❌	✅	4
Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems	❌	❌	✅	❌	❌	❌	✅	2
Two Routes to Scalable Credit Assignment without Weight Symmetry	❌	✅	✅	✅	✅	❌	✅	5
Two Simple Ways to Learn Individual Fairness Metrics from Data	✅	✅	✅	❌	❌	❌	❌	3
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels	❌	❌	✅	❌	❌	❌	✅	2
Uncertainty Estimation Using a Single Deep Deterministic Neural Network	❌	✅	✅	✅	✅	❌	✅	5
Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality	✅	❌	❌	❌	❌	❌	✅	2
Uncertainty-Aware Lookahead Factor Models for Quantitative Investing	❌	❌	❌	✅	✅	❌	✅	3
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere	✅	✅	✅	✅	❌	❌	✅	5
Understanding Self-Training for Gradual Domain Adaptation	❌	✅	✅	✅	❌	❌	✅	4
Understanding and Mitigating the Tradeoff between Robustness and Accuracy	✅	✅	✅	❌	❌	❌	✅	4
Understanding and Stabilizing GANs’ Training Dynamics Using Control Theory	✅	❌	✅	❌	✅	❌	✅	4
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling	❌	❌	❌	❌	❌	❌	❌	0
Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle	❌	❌	✅	❌	❌	❌	✅	2
Undirected Graphical Models as Approximate Posteriors	✅	✅	✅	❌	❌	❌	✅	4
UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training	✅	✅	✅	✅	✅	❌	✅	6
Uniform Convergence of Rank-weighted Learning	❌	✅	❌	❌	❌	❌	✅	2
Unique Properties of Flat Minima in Deep Networks	❌	❌	✅	❌	❌	❌	✅	2
Universal Average-Case Optimality of Polyak Momentum	❌	❌	❌	❌	❌	❌	❌	0
Universal Equivariant Multilayer Perceptrons	❌	❌	❌	❌	❌	❌	❌	0
Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift	❌	❌	✅	✅	❌	❌	✅	3
Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks	✅	✅	✅	✅	❌	❌	✅	5
Unsupervised Discovery of Interpretable Directions in the GAN Latent Space	❌	✅	✅	❌	✅	❌	✅	4
Unsupervised Speech Decomposition via Triple Information Bottleneck	❌	✅	✅	❌	❌	❌	✅	3
Unsupervised Transfer Learning for Spatiotemporal Predictive Networks	❌	✅	✅	✅	✅	✅	✅	6
Up or Down? Adaptive Rounding for Post-Training Quantization	❌	❌	✅	✅	✅	❌	✅	4
Upper bounds for Model-Free Row-Sparse Principal Component Analysis	✅	❌	❌	❌	✅	✅	✅	4
VFlow: More Expressive Generative Flows with Variational Data Augmentation	❌	✅	✅	✅	✅	❌	✅	5
Variable Skipping for Autoregressive Range Density Estimation	❌	✅	✅	❌	❌	❌	✅	3
Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems	✅	❌	❌	❌	❌	❌	✅	2
Variance Reduction and Quasi-Newton for Particle-Based Variational Inference	✅	❌	✅	❌	✅	❌	✅	4
Variance Reduction in Stochastic Particle-Optimization Sampling	✅	❌	✅	❌	❌	❌	✅	3
Variational Autoencoders with Riemannian Brownian Motion Priors	❌	❌	✅	❌	❌	❌	✅	2
Variational Bayesian Quantization	✅	✅	✅	❌	❌	❌	✅	4
Variational Imitation Learning with Diverse-quality Demonstrations	✅	✅	✅	❌	❌	❌	✅	4
Variational Inference for Sequential Data with Future Likelihood Estimates	❌	❌	✅	❌	❌	❌	✅	2
Variational Label Enhancement	❌	❌	✅	✅	❌	❌	✅	3
Video Prediction via Example Guidance	✅	✅	✅	❌	❌	❌	✅	4
VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video Processing	✅	✅	✅	✅	✅	✅	✅	7
Visual Grounding of Learned Physical Models	❌	❌	❌	❌	❌	❌	✅	1
Voice Separation with an Unknown Number of Multiple Speakers	❌	✅	✅	✅	❌	❌	✅	4
WaveFlow: A Compact Flow-based Model for Raw Audio	❌	✅	✅	❌	✅	❌	✅	4
Weakly-Supervised Disentanglement Without Compromises	❌	❌	✅	❌	✅	❌	✅	3
What Can Learned Intrinsic Rewards Capture?	✅	❌	❌	❌	❌	❌	❌	1
What can I do here? A Theory of Affordances in Reinforcement Learning	✅	✅	❌	❌	❌	❌	✅	3
What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?	✅	❌	❌	❌	❌	❌	❌	1
When Demands Evolve Larger and Noisier: Learning and Earning in a Growing Environment	✅	❌	❌	❌	❌	❌	❌	1
When Does Self-Supervision Help Graph Convolutional Networks?	❌	✅	✅	✅	❌	❌	✅	4
When Explanations Lie: Why Many Modified BP Attributions Fail	❌	✅	✅	❌	✅	❌	❌	3
When are Non-Parametric Methods Robust?	✅	❌	❌	❌	❌	❌	✅	2
When deep denoising meets iterative phase retrieval	✅	❌	❌	❌	❌	❌	✅	2
Which Tasks Should Be Learned Together in Multi-task Learning?	❌	✅	✅	✅	❌	❌	✅	4
Why Are Learned Indexes So Effective?	❌	✅	✅	❌	✅	❌	❌	3
Why bigger is not always better: on finite and infinite neural networks	❌	❌	✅	❌	❌	❌	✅	2
Word-Level Speech Recognition With a Letter to Word Encoder	❌	❌	✅	✅	❌	❌	✅	3
Working Memory Graphs	❌	✅	✅	❌	❌	❌	✅	3
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation	❌	✅	✅	✅	❌	❌	✅	4
XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning	✅	✅	✅	✅	❌	❌	✅	5
Zeno++: Robust Fully Asynchronous SGD	✅	❌	✅	✅	❌	❌	✅	4
k-means++: few more steps yield constant approximation	✅	❌	❌	❌	❌	❌	❌	1
p-Norm Flow Diffusion for Local Graph Clustering	✅	✅	✅	❌	❌	❌	✅	4
“Other-Play” for Zero-Shot Coordination	❌	✅	✅	❌	❌	❌	✅	3