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..

Conference on Neural Information Processing Systems (NeurIPS) - 2016

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
NeurIPS	2016	569	0.35	2.88	86.99%	29.09%

Search Papers

	Pseudocode	Open Source Code	Open Datasets	Dataset Splits	Hardware Specification	Software Dependencies	Experiment Setup
A Bandit Framework for Strategic Regression	✅	❌	❌	❌	❌	❌	❌	1
A Bayesian method for reducing bias in neural representational similarity analysis	❌	✅	❌	❌	❌	❌	✅	2
A Bio-inspired Redundant Sensing Architecture	❌	❌	❌	❌	❌	❌	✅	1
A Communication-Efficient Parallel Algorithm for Decision Tree	✅	✅	✅	❌	✅	❌	✅	5
A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order	✅	❌	✅	✅	✅	❌	✅	5
A Consistent Regularization Approach for Structured Prediction	❌	❌	✅	✅	❌	❌	❌	2
A Constant-Factor Bi-Criteria Approximation Guarantee for k-means++	✅	❌	❌	❌	❌	❌	❌	1
A Credit Assignment Compiler for Joint Prediction	✅	❌	✅	❌	❌	❌	❌	2
A Locally Adaptive Normal Distribution	✅	❌	✅	❌	❌	❌	✅	3
A Minimax Approach to Supervised Learning	❌	❌	✅	❌	❌	❌	✅	2
A Multi-Batch L-BFGS Method for Machine Learning	✅	❌	✅	❌	❌	❌	✅	3
A Multi-step Inertial Forward-Backward Splitting Method for Non-convex Optimization	✅	❌	❌	❌	❌	❌	✅	2
A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing	✅	✅	❌	❌	❌	❌	❌	2
A Non-generative Framework and Convex Relaxations for Unsupervised Learning	✅	❌	❌	❌	❌	❌	❌	1
A Non-parametric Learning Method for Confidently Estimating Patient's Clinical State and Dynamics	✅	❌	❌	❌	❌	❌	✅	2
A Powerful Generative Model Using Random Weights for the Deep Image Representation	❌	✅	✅	❌	❌	❌	✅	3
A Probabilistic Framework for Deep Learning	✅	❌	✅	✅	❌	❌	❌	3
A Probabilistic Model of Social Decision Making based on Reward Maximization	❌	❌	❌	❌	❌	❌	✅	1
A Probabilistic Programming Approach To Probabilistic Data Analysis	✅	❌	✅	❌	❌	❌	✅	3
A Pseudo-Bayesian Algorithm for Robust PCA	❌	❌	✅	❌	❌	❌	❌	1
A Simple Practical Accelerated Method for Finite Sums	✅	✅	✅	❌	❌	❌	✅	4
A Sparse Interactive Model for Matrix Completion with Side Information	✅	❌	✅	✅	❌	❌	✅	4
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks	❌	❌	✅	✅	✅	❌	✅	4
A Unified Approach for Learning the Parameters of Sum-Product Networks	❌	❌	❌	❌	❌	❌	✅	1
A forward model at Purkinje cell synapses facilitates cerebellar anticipatory control	❌	❌	❌	❌	❌	❌	✅	1
A posteriori error bounds for joint matrix decomposition problems	❌	❌	❌	❌	❌	❌	✅	1
A primal-dual method for conic constrained distributed optimization problems	✅	❌	❌	❌	❌	❌	✅	2
A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification	✅	❌	✅	✅	❌	❌	✅	4
A scaled Bregman theorem with applications	❌	❌	❌	❌	❌	❌	❌	0
A state-space model of cross-region dynamic connectivity in MEG/EEG	❌	✅	❌	❌	❌	❌	✅	2
Accelerating Stochastic Composition Optimization	✅	❌	✅	❌	❌	❌	✅	3
Achieving budget-optimality with adaptive schemes in crowdsourcing	✅	❌	❌	❌	❌	❌	✅	2
Achieving the KS threshold in the general stochastic block model with linearized acyclic belief propagation	✅	❌	❌	❌	❌	❌	❌	1
Active Learning from Imperfect Labelers	✅	❌	❌	❌	❌	❌	❌	1
Active Learning with Oracle Epiphany	✅	❌	✅	❌	❌	❌	❌	2
Active Nearest-Neighbor Learning in Metric Spaces	✅	❌	❌	❌	❌	❌	❌	1
Adaptive Averaging in Accelerated Descent Dynamics	✅	❌	❌	❌	❌	❌	❌	1
Adaptive Concentration Inequalities for Sequential Decision Problems	✅	❌	❌	❌	❌	❌	✅	2
Adaptive Maximization of Pointwise Submodular Functions With Budget Constraint	✅	❌	✅	❌	❌	❌	✅	3
Adaptive Neural Compilation	✅	✅	❌	❌	❌	❌	✅	3
Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy	✅	❌	✅	❌	❌	❌	✅	3
Adaptive Skills Adaptive Partitions (ASAP)	✅	❌	❌	❌	❌	❌	✅	2
Adaptive Smoothed Online Multi-Task Learning	✅	❌	✅	✅	❌	❌	✅	4
Adaptive optimal training of animal behavior	❌	❌	❌	❌	❌	❌	✅	1
Adversarial Multiclass Classification: A Risk Minimization Perspective	✅	❌	✅	✅	❌	❌	✅	4
Agnostic Estimation for Misspecified Phase Retrieval Models	✅	❌	❌	✅	❌	❌	✅	3
Algorithms and matching lower bounds for approximately-convex optimization	✅	❌	❌	❌	❌	❌	❌	1
An Architecture for Deep, Hierarchical Generative Models	❌	✅	✅	❌	❌	❌	❌	2
An Efficient Streaming Algorithm for the Submodular Cover Problem	✅	❌	✅	❌	❌	❌	✅	3
An Online Sequence-to-Sequence Model Using Partial Conditioning	❌	❌	✅	✅	❌	❌	✅	3
An algorithm for L1 nearest neighbor search via monotonic embedding	✅	❌	✅	✅	❌	❌	✅	4
An ensemble diversity approach to supervised binary hashing	❌	❌	✅	❌	❌	❌	✅	2
An equivalence between high dimensional Bayes optimal inference and M-estimation	❌	❌	❌	❌	❌	❌	✅	1
An urn model for majority voting in classification ensembles	❌	✅	✅	✅	❌	❌	✅	4
Ancestral Causal Inference	❌	✅	✅	❌	✅	✅	✅	5
Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm	✅	❌	✅	❌	❌	❌	❌	2
Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods	❌	❌	❌	❌	❌	❌	❌	0
Architectural Complexity Measures of Recurrent Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
Assortment Optimization Under the Mallows model	✅	❌	❌	❌	✅	✅	✅	4
Asynchronous Parallel Greedy Coordinate Descent	✅	❌	✅	✅	✅	❌	✅	5
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models	❌	❌	✅	❌	❌	❌	❌	1
Automated scalable segmentation of neurons from multispectral images	✅	❌	✅	❌	❌	❌	❌	2
Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks	❌	✅	❌	✅	✅	❌	✅	4
Average-case hardness of RIP certification	❌	❌	❌	❌	❌	❌	❌	0
Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction	✅	❌	❌	❌	❌	❌	❌	1
Backprop KF: Learning Discriminative Deterministic State Estimators	❌	❌	✅	✅	❌	❌	✅	3
Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition	❌	❌	❌	❌	❌	❌	❌	0
Barzilai-Borwein Step Size for Stochastic Gradient Descent	✅	❌	✅	❌	❌	❌	✅	3
Batched Gaussian Process Bandit Optimization via Determinantal Point Processes	✅	❌	✅	❌	❌	❌	✅	3
Bayesian Intermittent Demand Forecasting for Large Inventories	❌	❌	✅	✅	✅	❌	✅	4
Bayesian Optimization for Probabilistic Programs	❌	✅	❌	❌	❌	❌	✅	2
Bayesian Optimization with Robust Bayesian Neural Networks	❌	✅	✅	❌	❌	❌	✅	3
Bayesian Optimization with a Finite Budget: An Approximate Dynamic Programming Approach	❌	❌	❌	❌	❌	❌	✅	1
Bayesian latent structure discovery from multi-neuron recordings	❌	✅	✅	❌	✅	❌	✅	4
Bayesian optimization for automated model selection	❌	❌	✅	❌	❌	❌	✅	2
Bayesian optimization under mixed constraints with a slack-variable augmented Lagrangian	✅	✅	❌	❌	❌	✅	✅	4
Beyond Exchangeability: The Chinese Voting Process	❌	❌	✅	❌	❌	❌	❌	1
Bi-Objective Online Matching and Submodular Allocations	✅	❌	❌	❌	❌	❌	❌	1
Binarized Neural Networks	✅	✅	✅	✅	✅	✅	❌	6
Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning	✅	❌	❌	❌	❌	❌	❌	1
Blind Attacks on Machine Learners	❌	❌	❌	❌	❌	❌	❌	0
Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering	❌	❌	✅	❌	❌	❌	✅	2
Boosting with Abstention	✅	❌	✅	✅	❌	❌	✅	4
Bootstrap Model Aggregation for Distributed Statistical Learning	✅	❌	❌	❌	❌	❌	✅	2
Brains on Beats	❌	❌	✅	✅	❌	❌	✅	3
Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation	❌	❌	❌	❌	❌	❌	✅	1
Budgeted stream-based active learning via adaptive submodular maximization	✅	❌	✅	❌	❌	❌	✅	3
CMA-ES with Optimal Covariance Update and Storage Complexity	✅	✅	❌	❌	❌	❌	✅	3
CNNpack: Packing Convolutional Neural Networks in the Frequency Domain	❌	❌	✅	✅	✅	❌	✅	4
CRF-CNN: Modeling Structured Information in Human Pose Estimation	✅	❌	✅	❌	❌	❌	✅	3
Can Active Memory Replace Attention?	❌	✅	✅	✅	❌	❌	✅	4
Can Peripheral Representations Improve Clutter Metrics on Complex Scenes?	✅	✅	❌	❌	❌	❌	✅	3
Catching heuristics are optimal control policies	❌	❌	❌	❌	❌	❌	✅	1
Causal Bandits: Learning Good Interventions via Causal Inference	✅	✅	❌	❌	❌	❌	✅	3
Causal meets Submodular: Subset Selection with Directed Information	✅	❌	❌	❌	❌	❌	✅	2
CliqueCNN: Deep Unsupervised Exemplar Learning	❌	✅	✅	❌	✅	❌	✅	4
Clustering Signed Networks with the Geometric Mean of Laplacians	✅	❌	✅	❌	❌	❌	✅	3
Clustering with Bregman Divergences: an Asymptotic Analysis	❌	❌	❌	❌	❌	❌	✅	1
Clustering with Same-Cluster Queries	✅	❌	❌	❌	❌	❌	❌	1
Coevolutionary Latent Feature Processes for Continuous-Time User-Item Interactions	❌	❌	✅	✅	❌	❌	✅	3
Coin Betting and Parameter-Free Online Learning	✅	❌	✅	❌	❌	❌	❌	2
Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks	❌	❌	✅	✅	❌	❌	✅	3
Combinatorial Energy Learning for Image Segmentation	❌	❌	✅	✅	❌	❌	✅	3
Combinatorial Multi-Armed Bandit with General Reward Functions	✅	❌	❌	❌	❌	❌	❌	1
Combinatorial semi-bandit with known covariance	✅	❌	❌	❌	❌	❌	❌	1
Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning	❌	❌	❌	❌	❌	❌	❌	0
Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation	❌	❌	✅	✅	✅	✅	✅	5
Communication-Optimal Distributed Clustering	❌	❌	❌	❌	✅	❌	✅	2
Community Detection on Evolving Graphs	❌	❌	❌	❌	❌	❌	✅	1
Completely random measures for modelling block-structured sparse networks	❌	✅	❌	❌	❌	❌	✅	2
Composing graphical models with neural networks for structured representations and fast inference	✅	✅	✅	❌	❌	❌	✅	4
Computational and Statistical Tradeoffs in Learning to Rank	❌	❌	✅	❌	❌	❌	✅	2
Computing and maximizing influence in linear threshold and triggering models	❌	❌	❌	❌	❌	❌	✅	1
Conditional Generative Moment-Matching Networks	✅	❌	✅	✅	❌	❌	✅	4
Conditional Image Generation with PixelCNN Decoders	❌	❌	✅	❌	❌	❌	✅	2
Confusions over Time: An Interpretable Bayesian Model to Characterize Trends in Decision Making	❌	❌	❌	✅	❌	❌	✅	2
Consistent Estimation of Functions of Data Missing Non-Monotonically and Not at Random	❌	❌	✅	❌	❌	❌	❌	1
Consistent Kernel Mean Estimation for Functions of Random Variables	❌	❌	❌	❌	❌	❌	✅	1
Constraints Based Convex Belief Propagation	✅	❌	✅	❌	❌	❌	✅	3
Contextual semibandits via supervised learning oracles	✅	✅	✅	❌	❌	❌	✅	4
Convergence guarantees for kernel-based quadrature rules in misspecified settings	❌	❌	❌	❌	❌	❌	✅	1
Convex Two-Layer Modeling with Latent Structure	❌	❌	✅	✅	❌	❌	✅	3
Convolutional Neural Fabrics	❌	✅	✅	✅	❌	❌	✅	4
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering	❌	✅	✅	✅	❌	❌	✅	4
Cooperative Graphical Models	✅	✅	❌	❌	❌	❌	✅	3
Cooperative Inverse Reinforcement Learning	❌	❌	❌	❌	❌	❌	✅	1
Coordinate-wise Power Method	✅	❌	✅	❌	✅	❌	✅	4
Coresets for Scalable Bayesian Logistic Regression	✅	✅	✅	❌	❌	❌	✅	4
Correlated-PCA: Principal Components' Analysis when Data and Noise are Correlated	✅	❌	✅	❌	❌	❌	✅	3
Coupled Generative Adversarial Networks	❌	✅	✅	❌	❌	❌	✅	3
Crowdsourced Clustering: Querying Edges vs Triangles	❌	❌	✅	❌	❌	❌	✅	2
Cyclades: Conflict-free Asynchronous Machine Learning	✅	✅	✅	❌	✅	❌	✅	5
DECOrrelated feature space partitioning for distributed sparse regression	✅	❌	✅	✅	✅	❌	✅	5
DISCO Nets : DISsimilarity COefficients Networks	✅	❌	✅	✅	❌	❌	✅	4
Data Poisoning Attacks on Factorization-Based Collaborative Filtering	✅	❌	✅	❌	❌	❌	✅	3
Data Programming: Creating Large Training Sets, Quickly	❌	✅	✅	❌	❌	❌	❌	2
Data driven estimation of Laplace-Beltrami operator	❌	❌	❌	✅	❌	❌	✅	2
Deconvolving Feedback Loops in Recommender Systems	✅	❌	✅	❌	❌	❌	✅	3
Deep ADMM-Net for Compressive Sensing MRI	❌	❌	✅	❌	✅	❌	✅	3
Deep Alternative Neural Network: Exploring Contexts as Early as Possible for Action Recognition	❌	❌	✅	❌	❌	❌	✅	2
Deep Exploration via Bootstrapped DQN	✅	❌	✅	❌	❌	❌	✅	3
Deep Learning Games	✅	❌	✅	❌	❌	❌	✅	3
Deep Learning Models of the Retinal Response to Natural Scenes	❌	❌	❌	✅	✅	❌	✅	3
Deep Learning for Predicting Human Strategic Behavior	❌	❌	❌	✅	❌	❌	✅	2
Deep Learning without Poor Local Minima	❌	❌	❌	❌	❌	❌	❌	0
Deep Neural Networks with Inexact Matching for Person Re-Identification	❌	✅	✅	✅	✅	❌	✅	5
Deep Submodular Functions: Definitions and Learning	❌	❌	✅	❌	❌	❌	✅	2
DeepMath - Deep Sequence Models for Premise Selection	❌	❌	✅	✅	✅	❌	✅	4
Dense Associative Memory for Pattern Recognition	❌	❌	✅	❌	❌	❌	❌	1
Density Estimation via Discrepancy Based Adaptive Sequential Partition	✅	❌	✅	❌	❌	❌	✅	3
Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions	❌	✅	✅	✅	✅	❌	✅	5
Designing smoothing functions for improved worst-case competitive ratio in online optimization	✅	❌	❌	❌	❌	❌	✅	2
Dialog-based Language Learning	❌	❌	✅	✅	❌	❌	❌	2
Differential Privacy without Sensitivity	❌	❌	❌	❌	❌	❌	❌	0
Diffusion-Convolutional Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
Dimension-Free Iteration Complexity of Finite Sum Optimization Problems	❌	❌	❌	❌	❌	❌	❌	0
Dimensionality Reduction of Massive Sparse Datasets Using Coresets	✅	✅	✅	❌	❌	❌	✅	4
Direct Feedback Alignment Provides Learning in Deep Neural Networks	❌	❌	✅	❌	❌	❌	✅	2
Discriminative Gaifman Models	✅	❌	✅	❌	✅	❌	✅	4
Disease Trajectory Maps	❌	❌	❌	✅	❌	❌	✅	2
Disentangling factors of variation in deep representation using adversarial training	✅	❌	✅	✅	❌	❌	❌	3
Distributed Flexible Nonlinear Tensor Factorization	❌	❌	✅	✅	❌	❌	✅	3
Domain Separation Networks	❌	✅	✅	✅	❌	❌	✅	4
Double Thompson Sampling for Dueling Bandits	✅	✅	✅	❌	❌	❌	✅	4
Doubly Convolutional Neural Networks	✅	❌	✅	✅	✅	❌	✅	5
Dual Decomposed Learning with Factorwise Oracle for Structural SVM of Large Output Domain	✅	❌	✅	❌	❌	❌	❌	2
Dual Learning for Machine Translation	✅	❌	✅	✅	✅	❌	✅	5
Dual Space Gradient Descent for Online Learning	✅	❌	✅	✅	✅	❌	✅	5
Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions	✅	❌	✅	❌	❌	❌	✅	3
Dynamic Filter Networks	❌	✅	✅	❌	❌	❌	❌	2
Dynamic Mode Decomposition with Reproducing Kernels for Koopman Spectral Analysis	✅	✅	✅	❌	❌	❌	✅	4
Dynamic Network Surgery for Efficient DNNs	✅	✅	✅	❌	❌	❌	✅	4
Dynamic matrix recovery from incomplete observations under an exact low-rank constraint	❌	❌	❌	✅	❌	❌	✅	2
Edge-exchangeable graphs and sparsity	❌	❌	❌	❌	❌	❌	✅	1
Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis	✅	❌	✅	❌	❌	❌	✅	3
Efficient High-Order Interaction-Aware Feature Selection Based on Conditional Mutual Information	✅	✅	✅	✅	❌	❌	❌	4
Efficient Neural Codes under Metabolic Constraints	❌	❌	❌	❌	❌	❌	❌	0
Efficient Nonparametric Smoothness Estimation	❌	✅	❌	❌	❌	❌	❌	1
Efficient Second Order Online Learning by Sketching	✅	❌	✅	❌	❌	❌	✅	3
Efficient and Robust Spiking Neural Circuit for Navigation Inspired by Echolocating Bats	❌	❌	❌	❌	❌	❌	✅	1
Efficient state-space modularization for planning: theory, behavioral and neural signatures	❌	❌	✅	❌	❌	❌	❌	1
Eliciting Categorical Data for Optimal Aggregation	❌	❌	❌	❌	❌	❌	✅	1
End-to-End Goal-Driven Web Navigation	❌	✅	✅	✅	❌	❌	❌	3
End-to-End Kernel Learning with Supervised Convolutional Kernel Networks	❌	❌	✅	✅	✅	❌	✅	4
Equality of Opportunity in Supervised Learning	❌	❌	❌	❌	❌	❌	❌	0
Error Analysis of Generalized Nyström Kernel Regression	❌	❌	✅	❌	❌	❌	✅	2
Estimating Nonlinear Neural Response Functions using GP Priors and Kronecker Methods	❌	✅	❌	❌	❌	❌	✅	2
Estimating the Size of a Large Network and its Communities from a Random Sample	✅	❌	❌	❌	❌	❌	✅	2
Estimating the class prior and posterior from noisy positives and unlabeled data	❌	❌	✅	✅	❌	❌	✅	3
Exact Recovery of Hard Thresholding Pursuit	✅	❌	❌	❌	❌	❌	✅	2
Examples are not enough, learn to criticize! Criticism for Interpretability	✅	❌	✅	✅	❌	❌	✅	4
Exploiting Tradeoffs for Exact Recovery in Heterogeneous Stochastic Block Models	❌	❌	❌	❌	❌	❌	❌	0
Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters	✅	❌	✅	❌	❌	❌	✅	3
Exponential Family Embeddings	❌	❌	✅	✅	❌	❌	✅	3
Exponential expressivity in deep neural networks through transient chaos	❌	✅	❌	❌	❌	❌	✅	2
FPNN: Field Probing Neural Networks for 3D Data	❌	✅	✅	❌	✅	❌	✅	4
Fairness in Learning: Classic and Contextual Bandits	✅	❌	❌	❌	❌	❌	❌	1
Fast Active Set Methods for Online Spike Inference from Calcium Imaging	✅	❌	✅	❌	✅	❌	✅	4
Fast Algorithms for Robust PCA via Gradient Descent	✅	✅	✅	❌	✅	❌	✅	5
Fast Distributed Submodular Cover: Public-Private Data Summarization	✅	❌	❌	❌	✅	❌	✅	3
Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling	✅	❌	✅	❌	❌	❌	✅	3
Fast and Flexible Monotonic Functions with Ensembles of Lattices	❌	❌	✅	✅	❌	❌	✅	3
Fast and Provably Good Seedings for k-Means	✅	✅	✅	❌	❌	❌	❌	3
Fast and accurate spike sorting of high-channel count probes with KiloSort	❌	✅	✅	❌	❌	❌	❌	2
Fast learning rates with heavy-tailed losses	❌	❌	❌	❌	❌	❌	❌	0
Fast recovery from a union of subspaces	✅	❌	❌	❌	❌	❌	✅	2
Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimation	✅	✅	❌	❌	❌	❌	✅	3
Faster Projection-free Convex Optimization over the Spectrahedron	✅	❌	✅	❌	❌	❌	✅	3
Feature selection in functional data classification with recursive maxima hunting	✅	❌	✅	✅	❌	❌	✅	4
Feature-distributed sparse regression: a screen-and-clean approach	✅	❌	❌	❌	✅	❌	✅	3
Finding significant combinations of features in the presence of categorical covariates	✅	✅	✅	❌	❌	❌	✅	4
Finite Sample Prediction and Recovery Bounds for Ordinal Embedding	❌	❌	❌	❌	❌	❌	❌	0
Finite-Dimensional BFRY Priors and Variational Bayesian Inference for Power Law Models	❌	❌	✅	❌	❌	❌	✅	2
Finite-Sample Analysis of Fixed-k Nearest Neighbor Density Functional Estimators	❌	❌	❌	❌	❌	❌	❌	0
Flexible Models for Microclustering with Application to Entity Resolution	❌	❌	✅	❌	❌	❌	✅	2
Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities	❌	❌	❌	❌	❌	❌	❌	0
Full-Capacity Unitary Recurrent Neural Networks	❌	✅	✅	✅	❌	❌	✅	4
Fundamental Limits of Budget-Fidelity Trade-off in Label Crowdsourcing	❌	❌	❌	❌	❌	❌	❌	0
GAP Safe Screening Rules for Sparse-Group Lasso	✅	✅	✅	✅	❌	❌	✅	5
Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations	✅	✅	✅	✅	❌	❌	✅	5
Gaussian Processes for Survival Analysis	✅	❌	✅	✅	❌	❌	✅	4
General Tensor Spectral Co-clustering for Higher-Order Data	❌	✅	✅	❌	❌	❌	✅	3
Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back	❌	❌	❌	❌	❌	❌	❌	0
Generalized Correspondence-LDA Models (GC-LDA) for Identifying Functional Regions in the Brain	❌	❌	✅	✅	❌	❌	✅	3
Generating Images with Perceptual Similarity Metrics based on Deep Networks	❌	❌	✅	✅	❌	❌	✅	3
Generating Long-term Trajectories Using Deep Hierarchical Networks	❌	❌	❌	❌	❌	❌	❌	0
Generating Videos with Scene Dynamics	❌	❌	✅	❌	❌	❌	✅	2
Generative Adversarial Imitation Learning	✅	❌	✅	✅	❌	❌	✅	4
Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data	❌	❌	✅	❌	❌	❌	✅	2
Geometric Dirichlet Means Algorithm for topic inference	✅	❌	✅	✅	❌	❌	✅	4
Global Analysis of Expectation Maximization for Mixtures of Two Gaussians	❌	❌	❌	❌	❌	❌	❌	0
Global Optimality of Local Search for Low Rank Matrix Recovery	❌	❌	❌	❌	❌	❌	✅	1
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods	✅	❌	✅	✅	❌	❌	✅	4
Gradient-based Sampling: An Adaptive Importance Sampling for Least-squares	✅	❌	✅	❌	✅	❌	✅	4
Graph Clustering: Block-models and model free results	✅	❌	✅	❌	❌	❌	❌	2
Graphical Time Warping for Joint Alignment of Multiple Curves	❌	❌	✅	❌	❌	❌	✅	2
Graphons, mergeons, and so on!	✅	❌	❌	❌	❌	❌	✅	2
Greedy Feature Construction	✅	❌	✅	✅	❌	❌	✅	4
Guided Policy Search via Approximate Mirror Descent	✅	✅	❌	❌	❌	❌	✅	3
Hardness of Online Sleeping Combinatorial Optimization Problems	✅	❌	❌	❌	❌	❌	❌	1
Hierarchical Clustering via Spreading Metrics	✅	❌	✅	❌	❌	❌	✅	3
Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation	✅	❌	✅	❌	❌	❌	✅	3
Hierarchical Object Representation for Open-Ended Object Category Learning and Recognition	❌	❌	✅	✅	❌	❌	✅	3
Hierarchical Question-Image Co-Attention for Visual Question Answering	❌	✅	✅	✅	❌	✅	✅	5
High Dimensional Structured Superposition Models	❌	❌	❌	❌	❌	❌	✅	1
High resolution neural connectivity from incomplete tracing data using nonnegative spline regression	❌	✅	✅	✅	❌	❌	✅	4
High-Rank Matrix Completion and Clustering under Self-Expressive Models	❌	❌	✅	❌	❌	❌	✅	2
Higher-Order Factorization Machines	✅	❌	✅	✅	❌	❌	✅	4
Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than $O(1/\epsilon)$	✅	❌	✅	❌	❌	❌	❌	2
How Deep is the Feature Analysis underlying Rapid Visual Categorization?	❌	❌	✅	❌	❌	❌	❌	1
Human Decision-Making under Limited Time	❌	❌	❌	❌	❌	❌	✅	1
Hypothesis Testing in Unsupervised Domain Adaptation with Applications in Alzheimer's Disease	❌	❌	❌	❌	❌	❌	❌	0
Identification and Overidentification of Linear Structural Equation Models	✅	❌	❌	❌	❌	❌	❌	1
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections	❌	✅	✅	❌	❌	❌	✅	3
Improved Deep Metric Learning with Multi-class N-pair Loss Objective	❌	❌	✅	✅	❌	❌	✅	3
Improved Dropout for Shallow and Deep Learning	✅	❌	✅	✅	❌	❌	✅	4
Improved Error Bounds for Tree Representations of Metric Spaces	❌	✅	❌	❌	❌	❌	❌	1
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits	✅	❌	❌	❌	❌	❌	❌	1
Improved Techniques for Training GANs	❌	✅	✅	✅	❌	❌	✅	4
Improved Variational Inference with Inverse Autoregressive Flow	✅	✅	✅	❌	✅	❌	✅	5
Improving PAC Exploration Using the Median Of Means	✅	❌	❌	❌	❌	❌	❌	1
Incremental Boosting Convolutional Neural Network for Facial Action Unit Recognition	✅	❌	✅	✅	❌	❌	✅	4
Incremental Variational Sparse Gaussian Process Regression	❌	❌	✅	❌	❌	❌	✅	2
Inference by Reparameterization in Neural Population Codes	❌	❌	❌	❌	❌	❌	✅	1
Infinite Hidden Semi-Markov Modulated Interaction Point Process	✅	❌	✅	❌	❌	❌	✅	3
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets	❌	❌	✅	❌	❌	❌	✅	2
Integrated perception with recurrent multi-task neural networks	❌	❌	✅	✅	❌	❌	✅	3
Interaction Networks for Learning about Objects, Relations and Physics	❌	❌	❌	✅	❌	❌	✅	2
Interaction Screening: Efficient and Sample-Optimal Learning of Ising Models	❌	❌	❌	❌	❌	❌	✅	1
Interpretable Distribution Features with Maximum Testing Power	❌	✅	✅	✅	❌	❌	✅	4
Interpretable Nonlinear Dynamic Modeling of Neural Trajectories	❌	❌	❌	❌	❌	❌	✅	1
Iterative Refinement of the Approximate Posterior for Directed Belief Networks	✅	✅	✅	✅	❌	❌	✅	5
Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition	❌	❌	✅	✅	❌	❌	✅	3
Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization	❌	❌	✅	❌	❌	❌	✅	2
Joint quantile regression in vector-valued RKHSs	✅	❌	✅	✅	❌	✅	✅	5
Kernel Bayesian Inference with Posterior Regularization	❌	❌	❌	✅	❌	❌	✅	2
Kernel Observers: Systems-Theoretic Modeling and Inference of Spatiotemporally Evolving Processes	✅	❌	✅	❌	❌	❌	✅	3
Kronecker Determinantal Point Processes	✅	❌	✅	❌	✅	❌	✅	4
Ladder Variational Autoencoders	❌	✅	✅	❌	❌	❌	✅	3
Large Margin Discriminant Dimensionality Reduction in Prediction Space	✅	❌	✅	✅	❌	❌	✅	4
Large-Scale Price Optimization via Network Flow	✅	❌	❌	❌	✅	✅	✅	4
Latent Attention For If-Then Program Synthesis	❌	❌	❌	✅	❌	❌	✅	2
Launch and Iterate: Reducing Prediction Churn	❌	❌	✅	✅	❌	❌	✅	3
LazySVD: Even Faster SVD Decomposition Yet Without Agonizing Pain	✅	❌	✅	❌	✅	❌	❌	3
Learnable Visual Markers	❌	❌	❌	❌	❌	❌	✅	1
Learned Region Sparsity and Diversity Also Predicts Visual Attention	❌	❌	✅	✅	❌	❌	✅	3
Learning Additive Exponential Family Graphical Models via $\ell_{2,1}$-norm Regularized M-Estimation	❌	❌	❌	❌	❌	❌	✅	1
Learning Bayesian networks with ancestral constraints	❌	❌	✅	❌	✅	❌	✅	3
Learning Bound for Parameter Transfer Learning	❌	❌	❌	❌	❌	❌	❌	0
Learning Deep Embeddings with Histogram Loss	❌	✅	✅	✅	❌	❌	✅	4
Learning Deep Parsimonious Representations	✅	✅	✅	✅	❌	❌	✅	5
Learning HMMs with Nonparametric Emissions via Spectral Decompositions of Continuous Matrices	✅	✅	✅	❌	❌	❌	❌	3
Learning Infinite RBMs with Frank-Wolfe	✅	❌	✅	✅	❌	❌	✅	4
Learning Influence Functions from Incomplete Observations	❌	❌	✅	✅	❌	❌	✅	3
Learning Kernels with Random Features	✅	❌	✅	❌	❌	❌	✅	3
Learning Multiagent Communication with Backpropagation	❌	✅	✅	✅	❌	❌	✅	4
Learning Parametric Sparse Models for Image Super-Resolution	✅	❌	✅	❌	❌	❌	✅	3
Learning Sensor Multiplexing Design through Back-propagation	❌	✅	✅	✅	✅	❌	✅	5
Learning Sparse Gaussian Graphical Models with Overlapping Blocks	❌	✅	✅	✅	✅	❌	✅	5
Learning Structured Sparsity in Deep Neural Networks	❌	✅	✅	✅	✅	❌	✅	5
Learning Supervised PageRank with Gradient-Based and Gradient-Free Optimization Methods	✅	❌	❌	❌	❌	❌	✅	2
Learning Transferrable Representations for Unsupervised Domain Adaptation	✅	✅	✅	❌	❌	❌	✅	4
Learning Tree Structured Potential Games	✅	❌	✅	❌	❌	❌	✅	3
Learning Treewidth-Bounded Bayesian Networks with Thousands of Variables	❌	✅	✅	❌	❌	❌	✅	3
Learning User Perceived Clusters with Feature-Level Supervision	❌	❌	❌	❌	❌	❌	❌	0
Learning What and Where to Draw	❌	❌	✅	❌	❌	❌	✅	2
Learning a Metric Embedding for Face Recognition using the Multibatch Method	❌	❌	❌	❌	❌	❌	❌	0
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling	❌	❌	✅	✅	❌	❌	✅	3
Learning and Forecasting Opinion Dynamics in Social Networks	✅	❌	❌	❌	✅	❌	✅	3
Learning brain regions via large-scale online structured sparse dictionary learning	✅	❌	✅	❌	✅	❌	✅	4
Learning feed-forward one-shot learners	❌	❌	✅	✅	❌	❌	✅	3
Learning from Rational Behavior: Predicting Solutions to Unknown Linear Programs	❌	❌	❌	❌	❌	❌	❌	0
Learning from Small Sample Sets by Combining Unsupervised Meta-Training with CNNs	❌	❌	✅	✅	❌	❌	✅	3
Learning in Games: Robustness of Fast Convergence	✅	❌	❌	❌	❌	❌	❌	1
Learning shape correspondence with anisotropic convolutional neural networks	❌	❌	✅	✅	✅	❌	✅	4
Learning the Number of Neurons in Deep Networks	❌	❌	✅	✅	✅	❌	✅	4
Learning to Communicate with Deep Multi-Agent Reinforcement Learning	✅	✅	✅	❌	❌	❌	✅	4
Learning to Poke by Poking: Experiential Learning of Intuitive Physics	❌	❌	❌	❌	✅	❌	✅	2
Learning to learn by gradient descent by gradient descent	❌	❌	✅	✅	❌	❌	✅	3
Learning under uncertainty: a comparison between R-W and Bayesian approach	❌	❌	✅	❌	❌	❌	✅	2
Learning values across many orders of magnitude	✅	❌	✅	❌	❌	❌	✅	3
Leveraging Sparsity for Efficient Submodular Data Summarization	✅	❌	✅	❌	❌	❌	✅	3
Lifelong Learning with Weighted Majority Votes	✅	❌	❌	❌	❌	❌	❌	1
LightRNN: Memory and Computation-Efficient Recurrent Neural Networks	❌	❌	✅	✅	✅	❌	✅	4
Linear Contextual Bandits with Knapsacks	✅	❌	❌	❌	❌	❌	❌	1
Linear Feature Encoding for Reinforcement Learning	✅	❌	✅	✅	✅	❌	✅	5
Linear Relaxations for Finding Diverse Elements in Metric Spaces	✅	❌	✅	✅	❌	❌	✅	4
Linear dynamical neural population models through nonlinear embeddings	❌	✅	✅	✅	❌	❌	✅	4
Linear-Memory and Decomposition-Invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes	✅	❌	✅	❌	❌	❌	❌	2
Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences	❌	❌	❌	❌	❌	❌	❌	0
Local Minimax Complexity of Stochastic Convex Optimization	✅	❌	❌	❌	❌	❌	✅	2
Local Similarity-Aware Deep Feature Embedding	❌	❌	✅	❌	✅	❌	✅	3
Long-term Causal Effects via Behavioral Game Theory	✅	❌	❌	✅	❌	❌	✅	3
Low-Rank Regression with Tensor Responses	✅	❌	✅	✅	❌	❌	✅	4
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings	✅	❌	✅	❌	❌	❌	✅	3
Mapping Estimation for Discrete Optimal Transport	✅	❌	✅	✅	❌	❌	✅	4
Matching Networks for One Shot Learning	❌	❌	✅	✅	❌	❌	✅	3
Matrix Completion has No Spurious Local Minimum	❌	❌	❌	❌	❌	❌	❌	0
Maximal Sparsity with Deep Networks?	❌	❌	❌	❌	❌	❌	❌	0
Maximization of Approximately Submodular Functions	❌	❌	❌	❌	❌	❌	❌	0
Maximizing Influence in an Ising Network: A Mean-Field Optimal Solution	✅	❌	✅	❌	❌	❌	✅	3
Measuring Neural Net Robustness with Constraints	❌	❌	✅	❌	✅	❌	✅	3
Measuring the reliability of MCMC inference with bidirectional Monte Carlo	❌	❌	❌	❌	❌	❌	✅	1
Memory-Efficient Backpropagation Through Time	✅	❌	❌	❌	❌	❌	✅	2
MetaGrad: Multiple Learning Rates in Online Learning	✅	✅	❌	❌	❌	❌	❌	2
Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels	❌	❌	❌	❌	❌	❌	❌	0
Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning	✅	❌	✅	❌	❌	❌	❌	2
Minimizing Quadratic Functions in Constant Time	✅	✅	❌	✅	✅	❌	✅	5
Minimizing Regret on Reflexive Banach Spaces and Nash Equilibria in Continuous Zero-Sum Games	❌	❌	❌	❌	❌	❌	✅	1
Mistake Bounds for Binary Matrix Completion	✅	❌	❌	❌	❌	❌	❌	1
Mixed Linear Regression with Multiple Components	✅	❌	❌	❌	❌	❌	✅	2
Mixed vine copulas as joint models of spike counts and local field potentials	✅	❌	❌	❌	❌	❌	✅	2
MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild	❌	❌	✅	✅	❌	❌	✅	3
More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning	❌	❌	❌	❌	❌	❌	❌	0
Multi-armed Bandits: Competing with Optimal Sequences	✅	❌	❌	❌	❌	❌	❌	1
Multi-step learning and underlying structure in statistical models	❌	❌	❌	❌	❌	❌	❌	0
Multi-view Anomaly Detection via Robust Probabilistic Latent Variable Models	❌	❌	✅	❌	❌	❌	✅	2
Multimodal Residual Learning for Visual QA	❌	❌	✅	✅	❌	❌	✅	3
Multiple-Play Bandits in the Position-Based Model	✅	❌	✅	❌	❌	❌	✅	3
Multistage Campaigning in Social Networks	✅	✅	✅	❌	❌	❌	✅	4
Multivariate tests of association based on univariate tests	❌	❌	❌	❌	❌	❌	❌	0
Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula	❌	❌	❌	❌	❌	❌	❌	0
NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization	✅	❌	❌	❌	❌	❌	✅	2
Natural-Parameter Networks: A Class of Probabilistic Neural Networks	✅	❌	✅	✅	❌	❌	❌	3
Near-Optimal Smoothing of Structured Conditional Probability Matrices	✅	❌	✅	✅	❌	❌	✅	4
Nearly Isometric Embedding by Relaxation	✅	❌	✅	❌	❌	❌	✅	3
Nested Mini-Batch K-Means	✅	✅	✅	✅	❌	❌	✅	5
Neural Universal Discrete Denoiser	✅	❌	✅	❌	❌	❌	✅	3
Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks	✅	❌	✅	❌	✅	❌	✅	4
Neurons Equipped with Intrinsic Plasticity Learn Stimulus Intensity Statistics	❌	❌	✅	❌	❌	❌	✅	2
New Liftable Classes for First-Order Probabilistic Inference	❌	❌	❌	❌	✅	✅	✅	3
Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling	✅	❌	✅	❌	❌	❌	✅	3
Normalized Spectral Map Synchronization	✅	❌	✅	❌	❌	❌	❌	2
Object based Scene Representations using Fisher Scores of Local Subspace Projections	❌	❌	✅	✅	❌	❌	✅	3
Observational-Interventional Priors for Dose-Response Learning	❌	✅	✅	❌	❌	❌	✅	3
On Explore-Then-Commit strategies	✅	❌	❌	❌	❌	❌	✅	2
On Graph Reconstruction via Empirical Risk Minimization: Fast Learning Rates and Scalability	❌	❌	❌	❌	❌	❌	✅	1
On Mixtures of Markov Chains	❌	❌	✅	❌	❌	❌	✅	2
On Multiplicative Integration with Recurrent Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
On Regularizing Rademacher Observation Losses	✅	❌	✅	✅	❌	❌	✅	4
On Robustness of Kernel Clustering	✅	❌	❌	❌	❌	❌	✅	2
On Valid Optimal Assignment Kernels and Applications to Graph Classification	❌	❌	✅	✅	✅	❌	❌	3
On the Recursive Teaching Dimension of VC Classes	❌	❌	❌	❌	❌	✅	❌	1
One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities	❌	❌	✅	❌	❌	❌	✅	2
Online Bayesian Moment Matching for Topic Modeling with Unknown Number of Topics	✅	✅	✅	❌	❌	✅	✅	5
Online Convex Optimization with Unconstrained Domains and Losses	✅	❌	✅	❌	❌	❌	✅	3
Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes	❌	❌	❌	❌	❌	❌	❌	0
Online Pricing with Strategic and Patient Buyers	✅	❌	❌	❌	❌	❌	❌	1
Online and Differentially-Private Tensor Decomposition	✅	❌	❌	❌	❌	❌	❌	1
Only H is left: Near-tight Episodic PAC RL	❌	❌	✅	✅	❌	❌	✅	3
Operator Variational Inference	✅	❌	✅	❌	❌	❌	✅	3
Optimal Architectures in a Solvable Model of Deep Networks	❌	❌	✅	❌	❌	❌	❌	1
Optimal Binary Classifier Aggregation for General Losses	❌	❌	❌	❌	❌	❌	❌	0
Optimal Black-Box Reductions Between Optimization Objectives	✅	❌	✅	❌	❌	❌	❌	2
Optimal Cluster Recovery in the Labeled Stochastic Block Model	✅	❌	❌	❌	❌	❌	❌	1
Optimal Learning for Multi-pass Stochastic Gradient Methods	✅	❌	✅	❌	❌	❌	✅	3
Optimal Sparse Linear Encoders and Sparse PCA	✅	❌	✅	✅	❌	❌	✅	4
Optimal Tagging with Markov Chain Optimization	✅	❌	✅	❌	❌	❌	✅	3
Optimal spectral transportation with application to music transcription	❌	✅	✅	✅	❌	❌	✅	4
Optimistic Bandit Convex Optimization	✅	❌	❌	❌	❌	❌	❌	1
Optimistic Gittins Indices	✅	❌	❌	❌	❌	❌	✅	2
Optimizing affinity-based binary hashing using auxiliary coordinates	❌	❌	✅	✅	❌	❌	✅	3
Orthogonal Random Features	❌	❌	✅	❌	❌	❌	✅	2
PAC Reinforcement Learning with Rich Observations	✅	❌	❌	❌	❌	❌	❌	1
PAC-Bayesian Theory Meets Bayesian Inference	❌	❌	❌	❌	❌	❌	✅	1
Pairwise Choice Markov Chains	❌	✅	✅	✅	❌	❌	✅	4
Parameter Learning for Log-supermodular Distributions	✅	❌	✅	✅	❌	❌	✅	4
Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations	❌	❌	✅	✅	❌	❌	✅	3
PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions	❌	✅	✅	❌	✅	❌	✅	4
Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision	❌	✅	✅	❌	❌	✅	✅	4
Phased Exploration with Greedy Exploitation in Stochastic Combinatorial Partial Monitoring Games	✅	❌	❌	❌	❌	❌	❌	1
Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences	❌	❌	✅	❌	❌	❌	✅	2
Poisson-Gamma dynamical systems	❌	❌	✅	✅	❌	❌	✅	3
Preference Completion from Partial Rankings	✅	❌	✅	✅	❌	❌	❌	3
Privacy Odometers and Filters: Pay-as-you-Go Composition	✅	❌	❌	❌	❌	❌	❌	1
Probabilistic Inference with Generating Functions for Poisson Latent Variable Models	✅	❌	✅	❌	❌	❌	✅	3
Probabilistic Linear Multistep Methods	❌	❌	❌	❌	❌	❌	✅	1
Probing the Compositionality of Intuitive Functions	❌	❌	❌	❌	❌	❌	✅	1
Professor Forcing: A New Algorithm for Training Recurrent Networks	❌	❌	✅	✅	❌	❌	✅	3
Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images	❌	❌	✅	❌	❌	✅	✅	3
Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent	✅	❌	❌	❌	❌	❌	❌	1
Proximal Deep Structured Models	✅	❌	✅	❌	✅	✅	✅	5
Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization	✅	❌	✅	❌	❌	❌	✅	3
Pruning Random Forests for Prediction on a Budget	✅	❌	✅	✅	❌	✅	✅	5
Quantized Random Projections and Non-Linear Estimation of Cosine Similarity	❌	❌	✅	❌	❌	❌	✅	2
Quantum Perceptron Models	❌	❌	❌	❌	❌	❌	❌	0
R-FCN: Object Detection via Region-based Fully Convolutional Networks	❌	✅	✅	✅	✅	❌	✅	5
RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism	❌	✅	❌	✅	✅	✅	✅	5
Reconstructing Parameters of Spreading Models from Partial Observations	❌	❌	✅	❌	❌	❌	✅	2
Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates	✅	❌	❌	❌	❌	❌	❌	1
Refined Lower Bounds for Adversarial Bandits	❌	❌	❌	❌	❌	❌	❌	0
Regret Bounds for Non-decomposable Metrics with Missing Labels	✅	❌	✅	❌	✅	❌	✅	4
Regret of Queueing Bandits	✅	❌	❌	❌	❌	❌	✅	2
Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning	❌	❌	✅	✅	❌	❌	✅	3
Regularized Nonlinear Acceleration	✅	❌	✅	❌	❌	❌	✅	3
Relevant sparse codes with variational information bottleneck	❌	❌	✅	❌	❌	❌	❌	1
Reshaped Wirtinger Flow for Solving Quadratic System of Equations	✅	❌	❌	❌	✅	✅	✅	4
Residual Networks Behave Like Ensembles of Relatively Shallow Networks	❌	❌	✅	❌	❌	❌	❌	1
Review Networks for Caption Generation	❌	✅	✅	✅	✅	❌	✅	5
Reward Augmented Maximum Likelihood for Neural Structured Prediction	❌	❌	✅	✅	❌	❌	✅	3
Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds	✅	❌	❌	❌	❌	❌	✅	2
Robust Spectral Detection of Global Structures in the Data by Learning a Regularization	✅	✅	✅	❌	❌	❌	✅	4
Robust k-means: a Theoretical Revisit	❌	❌	❌	❌	❌	❌	✅	1
Robustness of classifiers: from adversarial to random noise	❌	❌	✅	❌	✅	❌	❌	2
Rényi Divergence Variational Inference	✅	✅	✅	✅	✅	❌	❌	5
SDP Relaxation with Randomized Rounding for Energy Disaggregation	✅	✅	✅	❌	❌	❌	✅	4
SEBOOST - Boosting Stochastic Learning Using Subspace Optimization Techniques	✅	✅	✅	❌	❌	❌	✅	4
SPALS: Fast Alternating Least Squares via Implicit Leverage Scores Sampling	✅	✅	✅	❌	✅	❌	✅	5
SURGE: Surface Regularized Geometry Estimation from a Single Image	❌	❌	✅	❌	❌	❌	✅	2
Safe Exploration in Finite Markov Decision Processes with Gaussian Processes	✅	✅	✅	❌	❌	❌	✅	4
Safe Policy Improvement by Minimizing Robust Baseline Regret	✅	❌	❌	❌	❌	❌	❌	1
Safe and Efficient Off-Policy Reinforcement Learning	❌	❌	✅	❌	❌	❌	❌	1
Sample Complexity of Automated Mechanism Design	❌	❌	❌	❌	❌	❌	❌	0
Sampling for Bayesian Program Learning	✅	❌	✅	✅	❌	❌	✅	4
Satisfying Real-world Goals with Dataset Constraints	✅	✅	✅	✅	❌	❌	✅	5
Scalable Adaptive Stochastic Optimization Using Random Projections	✅	❌	✅	❌	❌	❌	✅	3
Scaled Least Squares Estimator for GLMs in Large-Scale Problems	✅	❌	✅	❌	❌	❌	✅	3
Scaling Factorial Hidden Markov Models: Stochastic Variational Inference without Messages	❌	❌	✅	❌	✅	❌	✅	3
Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes	❌	❌	✅	❌	❌	❌	❌	1
Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much	✅	❌	❌	❌	❌	❌	✅	2
Search Improves Label for Active Learning	✅	❌	❌	❌	❌	❌	❌	1
Select-and-Sample for Spike-and-Slab Sparse Coding	✅	❌	✅	❌	❌	❌	✅	3
Selective inference for group-sparse linear models	✅	✅	✅	❌	❌	❌	✅	4
Semiparametric Differential Graph Models	❌	❌	✅	✅	❌	❌	✅	3
Sequential Neural Models with Stochastic Layers	✅	✅	✅	❌	✅	❌	❌	4
Short-Dot: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products	✅	❌	✅	❌	❌	❌	❌	2
Showing versus doing: Teaching by demonstration	✅	❌	❌	❌	❌	❌	✅	2
Simple and Efficient Weighted Minwise Hashing	✅	❌	✅	❌	✅	❌	✅	4
Single Pass PCA of Matrix Products	✅	✅	✅	❌	✅	✅	✅	6
Single-Image Depth Perception in the Wild	❌	❌	✅	✅	❌	❌	❌	2
Solving Marginal MAP Problems with NP Oracles and Parity Constraints	✅	❌	✅	❌	❌	❌	✅	3
Solving Random Systems of Quadratic Equations via Truncated Generalized Gradient Flow	✅	✅	❌	❌	❌	❌	✅	3
Sorting out typicality with the inverse moment matrix SOS polynomial	❌	❌	✅	❌	❌	❌	✅	2
SoundNet: Learning Sound Representations from Unlabeled Video	❌	❌	✅	✅	❌	❌	✅	3
Sparse Support Recovery with Non-smooth Loss Functions	❌	❌	❌	❌	❌	✅	✅	2
Spatio-Temporal Hilbert Maps for Continuous Occupancy Representation in Dynamic Environments	✅	❌	✅	❌	❌	❌	✅	3
Spatiotemporal Residual Networks for Video Action Recognition	❌	✅	✅	❌	✅	❌	✅	4
Spectral Learning of Dynamic Systems from Nonequilibrium Data	✅	❌	❌	❌	❌	❌	✅	2
Split LBI: An Iterative Regularization Path with Structural Sparsity	❌	❌	❌	❌	❌	❌	✅	1
Statistical Inference for Cluster Trees	❌	❌	✅	❌	❌	❌	✅	2
Statistical Inference for Pairwise Graphical Models Using Score Matching	❌	❌	✅	❌	❌	❌	❌	1
Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm	✅	✅	✅	✅	❌	❌	✅	5
Stochastic Gradient Geodesic MCMC Methods	✅	✅	✅	❌	❌	❌	✅	4
Stochastic Gradient MCMC with Stale Gradients	✅	❌	✅	❌	✅	❌	✅	4
Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo	✅	❌	✅	❌	✅	❌	✅	4
Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles	✅	❌	✅	✅	❌	❌	✅	4
Stochastic Online AUC Maximization	✅	❌	✅	✅	✅	❌	❌	4
Stochastic Optimization for Large-scale Optimal Transport	✅	❌	✅	❌	✅	❌	✅	4
Stochastic Structured Prediction under Bandit Feedback	✅	❌	✅	✅	❌	❌	✅	4
Stochastic Three-Composite Convex Minimization	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Variance Reduction Methods for Saddle-Point Problems	✅	❌	✅	❌	❌	❌	❌	2
Stochastic Variational Deep Kernel Learning	❌	✅	✅	❌	✅	❌	✅	4
Strategic Attentive Writer for Learning Macro-Actions	✅	❌	✅	❌	❌	❌	✅	3
Structure-Blind Signal Recovery	❌	❌	❌	❌	❌	❌	✅	1
Structured Matrix Recovery via the Generalized Dantzig Selector	❌	❌	❌	❌	❌	❌	❌	0
Structured Prediction Theory Based on Factor Graph Complexity	❌	❌	✅	✅	❌	❌	✅	3
Structured Sparse Regression via Greedy Hard Thresholding	✅	❌	✅	✅	✅	❌	✅	5
Sub-sampled Newton Methods with Non-uniform Sampling	✅	❌	✅	❌	❌	❌	✅	3
Sublinear Time Orthogonal Tensor Decomposition	✅	✅	✅	❌	✅	❌	✅	5
Supervised Learning with Tensor Networks	❌	✅	✅	❌	❌	❌	✅	3
Supervised Word Mover's Distance	✅	✅	✅	❌	❌	❌	✅	4
Supervised learning through the lens of compression	❌	❌	❌	❌	❌	❌	❌	0
Swapout: Learning an ensemble of deep architectures	❌	❌	✅	❌	❌	❌	✅	2
Synthesis of MCMC and Belief Propagation	✅	❌	❌	❌	❌	❌	✅	2
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks	❌	✅	✅	❌	❌	❌	✅	3
Tagger: Deep Unsupervised Perceptual Grouping	✅	✅	✅	✅	✅	❌	✅	6
Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction	❌	❌	✅	✅	❌	❌	✅	3
Tensor Switching Networks	❌	✅	✅	✅	❌	❌	✅	4
Testing for Differences in Gaussian Graphical Models: Applications to Brain Connectivity	✅	❌	✅	✅	❌	❌	✅	4
The Forget-me-not Process	✅	❌	✅	❌	❌	❌	✅	3
The Generalized Reparameterization Gradient	✅	❌	✅	✅	❌	❌	✅	4
The Limits of Learning with Missing Data	✅	❌	❌	❌	❌	❌	❌	1
The Multi-fidelity Multi-armed Bandit	✅	❌	❌	❌	❌	❌	❌	1
The Multiple Quantile Graphical Model	❌	❌	✅	❌	✅	❌	✅	3
The Multiscale Laplacian Graph Kernel	❌	❌	✅	✅	✅	❌	✅	4
The Parallel Knowledge Gradient Method for Batch Bayesian Optimization	✅	✅	✅	✅	❌	❌	✅	5
The Power of Adaptivity in Identifying Statistical Alternatives	✅	❌	❌	❌	❌	❌	❌	1
The Power of Optimization from Samples	✅	❌	❌	❌	❌	❌	❌	1
The Product Cut	✅	✅	✅	❌	❌	❌	✅	4
The Robustness of Estimator Composition	✅	❌	❌	❌	❌	❌	✅	2
The Sound of APALM Clapping: Faster Nonsmooth Nonconvex Optimization with Stochastic Asynchronous PALM	✅	❌	❌	❌	✅	❌	❌	2
The non-convex Burer-Monteiro approach works on smooth semidefinite programs	❌	❌	❌	❌	❌	❌	✅	1
Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning	❌	❌	✅	❌	❌	❌	✅	2
Threshold Bandits, With and Without Censored Feedback	✅	❌	❌	❌	❌	❌	❌	1
Threshold Learning for Optimal Decision Making	✅	✅	❌	❌	✅	❌	✅	4
Tight Complexity Bounds for Optimizing Composite Objectives	❌	❌	❌	❌	❌	❌	❌	0
Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers	❌	❌	❌	❌	❌	❌	❌	0
Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity	❌	❌	❌	❌	❌	❌	❌	0
Towards Conceptual Compression	❌	❌	✅	❌	❌	❌	✅	2
Towards Unifying Hamiltonian Monte Carlo and Slice Sampling	✅	❌	✅	❌	❌	❌	✅	3
Tracking the Best Expert in Non-stationary Stochastic Environments	✅	❌	❌	❌	❌	❌	❌	1
Tractable Operations for Arithmetic Circuits of Probabilistic Models	✅	❌	✅	❌	❌	❌	❌	2
Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images	❌	❌	✅	✅	❌	❌	✅	3
Tree-Structured Reinforcement Learning for Sequential Object Localization	❌	❌	✅	❌	✅	❌	✅	3
Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation	✅	❌	✅	❌	❌	❌	✅	3
Understanding Probabilistic Sparse Gaussian Process Approximations	❌	❌	✅	❌	❌	❌	✅	2
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks	❌	❌	✅	❌	❌	❌	❌	1
Unified Methods for Exploiting Piecewise Linear Structure in Convex Optimization	✅	❌	✅	❌	❌	❌	❌	2
Unifying Count-Based Exploration and Intrinsic Motivation	❌	❌	✅	❌	❌	❌	✅	2
Universal Correspondence Network	❌	❌	✅	✅	❌	❌	✅	3
Unsupervised Domain Adaptation with Residual Transfer Networks	❌	✅	✅	✅	❌	❌	✅	4
Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA	❌	❌	✅	✅	❌	❌	✅	3
Unsupervised Learning for Physical Interaction through Video Prediction	❌	✅	✅	✅	❌	❌	✅	4
Unsupervised Learning from Noisy Networks with Applications to Hi-C Data	❌	❌	✅	❌	❌	❌	❌	1
Unsupervised Learning of 3D Structure from Images	❌	❌	✅	❌	❌	❌	✅	2
Unsupervised Learning of Spoken Language with Visual Context	❌	❌	✅	✅	✅	❌	✅	4
Unsupervised Risk Estimation Using Only Conditional Independence Structure	✅	❌	✅	❌	❌	❌	✅	3
Using Fast Weights to Attend to the Recent Past	❌	❌	✅	✅	❌	❌	✅	3
Using Social Dynamics to Make Individual Predictions: Variational Inference with a Stochastic Kinetic Model	✅	✅	✅	❌	❌	❌	❌	3
VIME: Variational Information Maximizing Exploration	✅	❌	✅	❌	❌	❌	❌	2
Value Iteration Networks	❌	✅	❌	❌	❌	❌	❌	1
Variance Reduction in Stochastic Gradient Langevin Dynamics	✅	❌	✅	✅	❌	❌	✅	4
Variational Autoencoder for Deep Learning of Images, Labels and Captions	❌	❌	✅	✅	✅	❌	✅	4
Variational Bayes on Monte Carlo Steroids	✅	❌	✅	✅	❌	❌	✅	4
Variational Inference in Mixed Probabilistic Submodular Models	✅	❌	✅	✅	❌	❌	✅	4
Variational Information Maximization for Feature Selection	❌	✅	✅	✅	❌	❌	✅	4
Verification Based Solution for Structured MAB Problems	✅	❌	❌	❌	❌	❌	❌	1
Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks	❌	❌	✅	❌	❌	❌	✅	2
Visual Question Answering with Question Representation Update (QRU)	❌	❌	✅	✅	✅	❌	✅	4
Wasserstein Training of Restricted Boltzmann Machines	❌	❌	✅	✅	❌	❌	✅	3
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks	❌	✅	✅	✅	✅	❌	✅	5
What Makes Objects Similar: A Unified Multi-Metric Learning Approach	❌	❌	✅	✅	❌	❌	✅	3
Without-Replacement Sampling for Stochastic Gradient Methods	✅	❌	❌	❌	❌	❌	❌	1
Yggdrasil: An Optimized System for Training Deep Decision Trees at Scale	❌	✅	✅	❌	✅	✅	❌	4
beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data	❌	❌	✅	✅	❌	✅	✅	4
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization	✅	❌	✅	❌	❌	❌	✅	3
k*-Nearest Neighbors: From Global to Local	✅	❌	✅	✅	❌	❌	✅	4
“Congruent” and “Opposite” Neurons: Sisters for Multisensory Integration and Segregation	❌	❌	❌	❌	❌	❌	✅	1