reproducibilityindex.ai

Conference on Neural Information Processing Systems (NeurIPS) - 2018

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

$\ell_1$-regression with Heavy-tailed Distributions ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
(Probably) Concave Graph Matching ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
3D-Aware Scene Manipulation via Inverse Graphics ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
A Bandit Approach to Sequential Experimental Design with False Discovery Control ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
A Bayes-Sard Cubature Method ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
A Bayesian Approach to Generative Adversarial Imitation Learning ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
A Bayesian Nonparametric View on Count-Min Sketch ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
A Block Coordinate Ascent Algorithm for Mean-Variance Optimization ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
A Bridging Framework for Model Optimization and Deep Propagation ❌ ❌ ✅ ❌ ✅ ❌ ❌ 2
A Convex Duality Framework for GANs ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
A Dual Framework for Low-rank Tensor Completion ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
A General Method for Amortizing Variational Filtering ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks ❌ ✅ ❌ ✅ ✅ ❌ ✅ 4
A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication ✅ ❌ ✅ ❌ ✅ ✅ ✅ 5
A Lyapunov-based Approach to Safe Reinforcement Learning ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
A Mathematical Model For Optimal Decisions In A Representative Democracy ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
A Model for Learned Bloom Filters and Optimizing by Sandwiching ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
A Neural Compositional Paradigm for Image Captioning ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
A Practical Algorithm for Distributed Clustering and Outlier Detection ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
A Probabilistic U-Net for Segmentation of Ambiguous Images ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
A Reduction for Efficient LDA Topic Reconstruction ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
A Retrieve-and-Edit Framework for Predicting Structured Outputs ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
A Simple Cache Model for Image Recognition ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks ✅ ✅ ✅ ✅ ❌ ❌ ❌ 4
A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
A Smoother Way to Train Structured Prediction Models ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
A Spectral View of Adversarially Robust Features ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
A Statistical Recurrent Model on the Manifold of Symmetric Positive Definite Matrices ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
A Stein variational Newton method ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
A Structured Prediction Approach for Label Ranking ❌ ✅ ✅ ✅ ❌ ❌ ❌ 3
A Theory-Based Evaluation of Nearest Neighbor Models Put Into Practice ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
A Unified Framework for Extensive-Form Game Abstraction with Bounds ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
A Unified View of Piecewise Linear Neural Network Verification ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
A convex program for bilinear inversion of sparse vectors ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
A flexible model for training action localization with varying levels of supervision ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
A loss framework for calibrated anomaly detection ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
A no-regret generalization of hierarchical softmax to extreme multi-label classification ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
A probabilistic population code based on neural samples ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
ATOMO: Communication-efficient Learning via Atomic Sparsification ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
A^2-Nets: Double Attention Networks ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Acceleration through Optimistic No-Regret Dynamics ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Active Learning for Non-Parametric Regression Using Purely Random Trees ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Active Matting ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Adaptation to Easy Data in Prediction with Limited Advice ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Adaptive Learning with Unknown Information Flows ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Adaptive Methods for Nonconvex Optimization ✅ ❌ ✅ ✅ ✅ ❌ ✅ 5
Adaptive Negative Curvature Descent with Applications in Non-convex Optimization ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Adaptive Online Learning in Dynamic Environments ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Adaptive Path-Integral Autoencoders: Representation Learning and Planning for Dynamical Systems ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Adaptive Sampling Towards Fast Graph Representation Learning ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models ✅ ✅ ❌ ✅ ❌ ❌ ✅ 4
Adding One Neuron Can Eliminate All Bad Local Minima ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Adversarial Attacks on Stochastic Bandits ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Adversarial Examples that Fool both Computer Vision and Time-Limited Humans ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Adversarial Multiple Source Domain Adaptation ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Adversarial Regularizers in Inverse Problems ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Adversarial Scene Editing: Automatic Object Removal from Weak Supervision ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Adversarial Text Generation via Feature-Mover's Distance ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Adversarial vulnerability for any classifier ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Adversarially Robust Generalization Requires More Data ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Adversarially Robust Optimization with Gaussian Processes ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Algebraic tests of general Gaussian latent tree models ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Algorithmic Linearly Constrained Gaussian Processes ❌ ❌ ❌ ❌ ❌ ✅ ✅ 2
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Algorithms and Theory for Multiple-Source Adaptation ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs ✅ ❌ ❌ ❌ ✅ ❌ ✅ 3
Alternating optimization of decision trees, with application to learning sparse oblique trees ✅ ❌ ✅ ✅ ✅ ❌ ✅ 5
Amortized Inference Regularization ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
An Efficient Pruning Algorithm for Robust Isotonic Regression ✅ ❌ ❌ ❌ ✅ ❌ ✅ 3
An Improved Analysis of Alternating Minimization for Structured Multi-Response Regression ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
An Information-Theoretic Analysis for Thompson Sampling with Many Actions ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
An Off-policy Policy Gradient Theorem Using Emphatic Weightings ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
An intriguing failing of convolutional neural networks and the CoordConv solution ❌ ✅ ✅ ✅ ❌ ❌ ❌ 3
Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Analytic solution and stationary phase approximation for the Bayesian lasso and elastic net ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Approximate Knowledge Compilation by Online Collapsed Importance Sampling ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Approximating Real-Time Recurrent Learning with Random Kronecker Factors ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Approximation algorithms for stochastic clustering ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Are GANs Created Equal? A Large-Scale Study ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Are ResNets Provably Better than Linear Predictors? ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Assessing Generative Models via Precision and Recall ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Asymptotic optimality of adaptive importance sampling ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples ❌ ✅ ✅ ✅ ❌ ✅ ✅ 5
Attention in Convolutional LSTM for Gesture Recognition ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific Language ❌ ✅ ❌ ❌ ❌ ❌ ✅ 2
Automatic Program Synthesis of Long Programs with a Learned Garbage Collector ❌ ✅ ❌ ❌ ✅ ❌ ✅ 3
Automatic differentiation in ML: Where we are and where we should be going ❌ ✅ ❌ ❌ ❌ ❌ ❌ 1
Automating Bayesian optimization with Bayesian optimization ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
BML: A High-performance, Low-cost Gradient Synchronization Algorithm for DML Training ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
BRITS: Bidirectional Recurrent Imputation for Time Series ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
BRUNO: A Deep Recurrent Model for Exchangeable Data ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Balanced Policy Evaluation and Learning ❌ ❌ ✅ ❌ ❌ ✅ ✅ 3
Banach Wasserstein GAN ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Bandit Learning in Concave N-Person Games ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Bandit Learning with Implicit Feedback ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Bandit Learning with Positive Externalities ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Bayesian Adversarial Learning ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Bayesian Alignments of Warped Multi-Output Gaussian Processes ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Bayesian Control of Large MDPs with Unknown Dynamics in Data-Poor Environments ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Bayesian Distributed Stochastic Gradient Descent ❌ ❌ ✅ ✅ ✅ ❌ ❌ 3
Bayesian Inference of Temporal Task Specifications from Demonstrations ✅ ❌ ❌ ❌ ✅ ❌ ✅ 3
Bayesian Model Selection Approach to Boundary Detection with Non-Local Priors ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Bayesian Model-Agnostic Meta-Learning ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Bayesian Nonparametric Spectral Estimation ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Bayesian Semi-supervised Learning with Graph Gaussian Processes ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Bayesian Structure Learning by Recursive Bootstrap ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Beauty-in-averageness and its contextual modulations: A Bayesian statistical account ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Benefits of over-parameterization with EM ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Beyond Grids: Learning Graph Representations for Visual Recognition ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Bias and Generalization in Deep Generative Models: An Empirical Study ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Bilevel Distance Metric Learning for Robust Image Recognition ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Bilevel learning of the Group Lasso structure ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Bilinear Attention Networks ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
BinGAN: Learning Compact Binary Descriptors with a Regularized GAN ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Binary Classification from Positive-Confidence Data ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Binary Rating Estimation with Graph Side Information ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Bipartite Stochastic Block Models with Tiny Clusters ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Blind Deconvolutional Phase Retrieval via Convex Programming ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Blockwise Parallel Decoding for Deep Autoregressive Models ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
Boolean Decision Rules via Column Generation ❌ ❌ ✅ ✅ ❌ ✅ ✅ 4
Boosted Sparse and Low-Rank Tensor Regression ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
Boosting Black Box Variational Inference ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Bounded-Loss Private Prediction Markets ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
BourGAN: Generative Networks with Metric Embeddings ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Breaking the Activation Function Bottleneck through Adaptive Parameterization ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Breaking the Span Assumption Yields Fast Finite-Sum Minimization ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
But How Does It Work in Theory? Linear SVM with Random Features ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Byzantine Stochastic Gradient Descent ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
COLA: Decentralized Linear Learning ✅ ✅ ✅ ❌ ✅ ❌ ❌ 4
Can We Gain More from Orthogonality Regularizations in Training Deep Networks? ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces ❌ ✅ ✅ ✅ ❌ ❌ ❌ 3
CatBoost: unbiased boosting with categorical features ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
Causal Discovery from Discrete Data using Hidden Compact Representation ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Causal Inference and Mechanism Clustering of A Mixture of Additive Noise Models ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Causal Inference via Kernel Deviance Measures ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Causal Inference with Noisy and Missing Covariates via Matrix Factorization ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Chain of Reasoning for Visual Question Answering ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Chaining Mutual Information and Tightening Generalization Bounds ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Clebsch–Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Cluster Variational Approximations for Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Clustering Redemption–Beyond the Impossibility of Kleinberg’s Axioms ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Co-regularized Alignment for Unsupervised Domain Adaptation ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Co-teaching: Robust training of deep neural networks with extremely noisy labels ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Collaborative Learning for Deep Neural Networks ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Communication Compression for Decentralized Training ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Communication Efficient Parallel Algorithms for Optimization on Manifolds ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Community Exploration: From Offline Optimization to Online Learning ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Compact Generalized Non-local Network ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Compact Representation of Uncertainty in Clustering ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Completing State Representations using Spectral Learning ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Complex Gated Recurrent Neural Networks ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Computationally and statistically efficient learning of causal Bayes nets using path queries ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Computing Higher Order Derivatives of Matrix and Tensor Expressions ❌ ✅ ❌ ❌ ✅ ✅ ✅ 4
Computing Kantorovich-Wasserstein Distances on $d$-dimensional histograms using $(d+1)$-partite graphs ❌ ✅ ✅ ❌ ✅ ✅ ✅ 5
Conditional Adversarial Domain Adaptation ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Confounding-Robust Policy Improvement ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Connecting Optimization and Regularization Paths ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Connectionist Temporal Classification with Maximum Entropy Regularization ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Constant Regret, Generalized Mixability, and Mirror Descent ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Constrained Cross-Entropy Method for Safe Reinforcement Learning ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Constrained Graph Variational Autoencoders for Molecule Design ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Constructing Deep Neural Networks by Bayesian Network Structure Learning ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Constructing Fast Network through Deconstruction of Convolution ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Constructing Unrestricted Adversarial Examples with Generative Models ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Contamination Attacks and Mitigation in Multi-Party Machine Learning ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Content preserving text generation with attribute controls ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Context-aware Synthesis and Placement of Object Instances ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Context-dependent upper-confidence bounds for directed exploration ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Contextual Combinatorial Multi-armed Bandits with Volatile Arms and Submodular Reward ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Contextual Pricing for Lipschitz Buyers ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Contextual Stochastic Block Models ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Contextual bandits with surrogate losses: Margin bounds and efficient algorithms ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Contour location via entropy reduction leveraging multiple information sources ❌ ✅ ❌ ❌ ❌ ✅ ✅ 3
Contrastive Learning from Pairwise Measurements ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Convergence of Cubic Regularization for Nonconvex Optimization under KL Property ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Convex Elicitation of Continuous Properties ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification ✅ ❌ ✅ ✅ ✅ ❌ ✅ 5
Coordinate Descent with Bandit Sampling ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Coupled Variational Bayes via Optimization Embedding ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Credit Assignment For Collective Multiagent RL With Global Rewards ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Critical initialisation for deep signal propagation in noisy rectifier neural networks ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
DAGs with NO TEARS: Continuous Optimization for Structure Learning ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Data Amplification: A Unified and Competitive Approach to Property Estimation ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Data center cooling using model-predictive control ❌ ❌ ❌ ✅ ❌ ❌ ✅ 2
Data-Driven Clustering via Parameterized Lloyd's Families ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Data-Efficient Hierarchical Reinforcement Learning ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Data-dependent PAC-Bayes priors via differential privacy ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenters ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Deep Anomaly Detection Using Geometric Transformations ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Deep Attentive Tracking via Reciprocative Learning ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Deep Defense: Training DNNs with Improved Adversarial Robustness ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Deep Dynamical Modeling and Control of Unsteady Fluid Flows ❌ ✅ ❌ ❌ ✅ ❌ ✅ 3
Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Deep Generative Markov State Models ❌ ✅ ✅ ✅ ❌ ❌ ❌ 3
Deep Generative Models for Distribution-Preserving Lossy Compression ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Deep Generative Models with Learnable Knowledge Constraints ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Deep Homogeneous Mixture Models: Representation, Separation, and Approximation ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Deep Network for the Integrated 3D Sensing of Multiple People in Natural Images ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Deep Neural Nets with Interpolating Function as Output Activation ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Deep Neural Networks with Box Convolutions ❌ ✅ ✅ ✅ ✅ ✅ ✅ 6
Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Deep Poisson gamma dynamical systems ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Deep Predictive Coding Network with Local Recurrent Processing for Object Recognition ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Deep Reinforcement Learning of Marked Temporal Point Processes ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Deep State Space Models for Time Series Forecasting ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Deep State Space Models for Unconditional Word Generation ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Deep Structured Prediction with Nonlinear Output Transformations ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Deep, complex, invertible networks for inversion of transmission effects in multimode optical fibres ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
DeepPINK: reproducible feature selection in deep neural networks ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
DeepProbLog: Neural Probabilistic Logic Programming ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Deepcode: Feedback Codes via Deep Learning ❌ ✅ ❌ ❌ ❌ ❌ ✅ 2
Delta-encoder: an effective sample synthesis method for few-shot object recognition ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Demystifying excessively volatile human learning: A Bayesian persistent prior and a neural approximation ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Dendritic cortical microcircuits approximate the backpropagation algorithm ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Densely Connected Attention Propagation for Reading Comprehension ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Depth-Limited Solving for Imperfect-Information Games ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Derivative Estimation in Random Design ❌ ❌ ❌ ❌ ❌ ✅ ✅ 2
Designing by Training: Acceleration Neural Network for Fast High-Dimensional Convolution ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Dialog-based Interactive Image Retrieval ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
DifNet: Semantic Segmentation by Diffusion Networks ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Differentiable MPC for End-to-end Planning and Control ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Differential Privacy for Growing Databases ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
Differentially Private Bayesian Inference for Exponential Families ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Differentially Private Change-Point Detection ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Differentially Private Contextual Linear Bandits ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Differentially Private Robust Low-Rank Approximation ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Differentially Private Testing of Identity and Closeness of Discrete Distributions ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Differentially Private Uniformly Most Powerful Tests for Binomial Data ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Differentially Private k-Means with Constant Multiplicative Error ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Diffusion Maps for Textual Network Embedding ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Diminishing Returns Shape Constraints for Interpretability and Regularization ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Direct Estimation of Differences in Causal Graphs ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Direct Runge-Kutta Discretization Achieves Acceleration ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Dirichlet belief networks for topic structure learning ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Disconnected Manifold Learning for Generative Adversarial Networks ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Discretely Relaxing Continuous Variables for tractable Variational Inference ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Discrimination-aware Channel Pruning for Deep Neural Networks ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Distilled Wasserstein Learning for Word Embedding and Topic Modeling ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Distributed $k$-Clustering for Data with Heavy Noise ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Distributed Multi-Player Bandits - a Game of Thrones Approach ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Distributed Multitask Reinforcement Learning with Quadratic Convergence ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Distributed Stochastic Optimization via Adaptive SGD ✅ ❌ ✅ ✅ ❌ ✅ ✅ 5
Distributed Weight Consolidation: A Brain Segmentation Case Study ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Distributionally Robust Graphical Models ❌ ❌ ✅ ✅ ❌ ❌ ❌ 2
Diverse Ensemble Evolution: Curriculum Data-Model Marriage ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Diversity-Driven Exploration Strategy for Deep Reinforcement Learning ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Do Less, Get More: Streaming Submodular Maximization with Subsampling ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Does mitigating ML's impact disparity require treatment disparity? ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions ❌ ✅ ✅ ❌ ❌ ✅ ✅ 4
Domain-Invariant Projection Learning for Zero-Shot Recognition ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with $\beta$-Divergences ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
DropBlock: A regularization method for convolutional networks ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
DropMax: Adaptive Variational Softmax ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Dropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization ✅ ❌ ✅ ✅ ❌ ❌ ❌ 3
Dual Policy Iteration ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Dual Swap Disentangling ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Dynamic Network Model from Partial Observations ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Early Stopping for Nonparametric Testing ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Efficient Anomaly Detection via Matrix Sketching ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Efficient Convex Completion of Coupled Tensors using Coupled Nuclear Norms ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Efficient Formal Safety Analysis of Neural Networks ❌ ❌ ✅ ❌ ❌ ✅ ✅ 3
Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses ✅ ❌ ✅ ✅ ❌ ❌ ❌ 3
Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Efficient Loss-Based Decoding on Graphs for Extreme Classification ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Efficient Neural Network Robustness Certification with General Activation Functions ❌ ✅ ✅ ❌ ✅ ❌ ❌ 3
Efficient Online Portfolio with Logarithmic Regret ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Efficient Projection onto the Perfect Phylogeny Model ✅ ✅ ❌ ❌ ✅ ❌ ❌ 3
Efficient Stochastic Gradient Hard Thresholding ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Efficient inference for time-varying behavior during learning ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Efficient nonmyopic batch active search ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Efficient online algorithms for fast-rate regret bounds under sparsity ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Embedding Logical Queries on Knowledge Graphs ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Empirical Risk Minimization Under Fairness Constraints ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
End-to-End Differentiable Physics for Learning and Control ❌ ✅ ❌ ✅ ❌ ❌ ✅ 3
End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems ❌ ✅ ✅ ✅ ❌ ❌ ❌ 3
Enhancing the Accuracy and Fairness of Human Decision Making ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Entropy Rate Estimation for Markov Chains with Large State Space ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Entropy and mutual information in models of deep neural networks ❌ ✅ ❌ ❌ ✅ ❌ ❌ 2
Equality of Opportunity in Classification: A Causal Approach ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Escaping Saddle Points in Constrained Optimization ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Estimating Learnability in the Sublinear Data Regime ✅ ✅ ✅ ❌ ✅ ✅ ✅ 6
Estimators for Multivariate Information Measures in General Probability Spaces ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Evidential Deep Learning to Quantify Classification Uncertainty ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Evolution-Guided Policy Gradient in Reinforcement Learning ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Evolved Policy Gradients ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Ex ante coordination and collusion in zero-sum multi-player extensive-form games ✅ ❌ ✅ ❌ ❌ ✅ ✅ 4
Exact natural gradient in deep linear networks and its application to the nonlinear case ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Expanding Holographic Embeddings for Knowledge Completion ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Experimental Design for Cost-Aware Learning of Causal Graphs ✅ ❌ ❌ ❌ ❌ ✅ ✅ 3
Explaining Deep Learning Models -- A Bayesian Non-parametric Approach ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Exploiting Numerical Sparsity for Efficient Learning : Faster Eigenvector Computation and Regression ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Exploration in Structured Reinforcement Learning ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Exponentially Weighted Imitation Learning for Batched Historical Data ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Exponentiated Strongly Rayleigh Distributions ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Extracting Relationships by Multi-Domain Matching ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
FRAGE: Frequency-Agnostic Word Representation ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Factored Bandits ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Fairness Through Computationally-Bounded Awareness ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Faithful Inversion of Generative Models for Effective Amortized Inference ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Fast Estimation of Causal Interactions using Wold Processes ✅ ✅ ✅ ❌ ✅ ✅ ✅ 6
Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity ✅ ❌ ✅ ❌ ✅ ❌ ❌ 3
Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions ✅ ❌ ✅ ✅ ❌ ❌ ❌ 3
Fast Similarity Search via Optimal Sparse Lifting ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Fast and Effective Robustness Certification ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Fast deep reinforcement learning using online adjustments from the past ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Fast greedy algorithms for dictionary selection with generalized sparsity constraints ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Faster Neural Networks Straight from JPEG ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Fighting Boredom in Recommender Systems with Linear Reinforcement Learning ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Flexible and accurate inference and learning for deep generative models ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Flexible neural representation for physics prediction ✅ ✅ ❌ ❌ ❌ ❌ ❌ 2
Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks ❌ ✅ ❌ ✅ ❌ ❌ ✅ 3
Foreground Clustering for Joint Segmentation and Localization in Videos and Images ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger ❌ ✅ ✅ ✅ ❌ ❌ ❌ 3
Found Graph Data and Planted Vertex Covers ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Frequency-Domain Dynamic Pruning for Convolutional Neural Networks ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
From Stochastic Planning to Marginal MAP ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Fully Understanding The Hashing Trick ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
GIANT: Globally Improved Approximate Newton Method for Distributed Optimization ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
GILBO: One Metric to Measure Them All ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
GLoMo: Unsupervised Learning of Transferable Relational Graphs ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata Influence ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Gaussian Process Conditional Density Estimation ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Gaussian Process Prior Variational Autoencoders ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Generalisation in humans and deep neural networks ❌ ✅ ✅ ❌ ❌ ✅ ✅ 4
Generalisation of structural knowledge in the hippocampal-entorhinal system ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Generalization Bounds for Uniformly Stable Algorithms ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Generalized Inverse Optimization through Online Learning ✅ ❌ ❌ ❌ ✅ ❌ ✅ 3
Generalized Zero-Shot Learning with Deep Calibration Network ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Generalizing Graph Matching beyond Quadratic Assignment Model ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Generalizing Tree Probability Estimation via Bayesian Networks ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Generalizing to Unseen Domains via Adversarial Data Augmentation ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization ❌ ❌ ❌ ✅ ✅ ❌ ✅ 3
Generative Neural Machine Translation ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Generative Probabilistic Novelty Detection with Adversarial Autoencoders ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Generative modeling for protein structures ❌ ❌ ✅ ❌ ❌ ✅ ❌ 2
Genetic-Gated Networks for Deep Reinforcement Learning ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Geometrically Coupled Monte Carlo Sampling ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Geometry Based Data Generation ✅ ✅ ✅ ✅ ❌ ❌ ❌ 4
Geometry-Aware Recurrent Neural Networks for Active Visual Recognition ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Global Gated Mixture of Second-order Pooling for Improving Deep Convolutional Neural Networks ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Global Geometry of Multichannel Sparse Blind Deconvolution on the Sphere ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Global Non-convex Optimization with Discretized Diffusions ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Glow: Generative Flow with Invertible 1x1 Convolutions ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Gradient Descent Meets Shift-and-Invert Preconditioning for Eigenvector Computation ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Gradient Descent for Spiking Neural Networks ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Gradient Sparsification for Communication-Efficient Distributed Optimization ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Graphical Generative Adversarial Networks ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
Graphical model inference: Sequential Monte Carlo meets deterministic approximations ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Group Equivariant Capsule Networks ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
GumBolt: Extending Gumbel trick to Boltzmann priors ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
HOGWILD!-Gibbs can be PanAccurate ✅ ❌ ❌ ❌ ✅ ❌ ✅ 3
HOUDINI: Lifelong Learning as Program Synthesis ❌ ✅ ✅ ❌ ✅ ❌ ❌ 3
Hamiltonian Variational Auto-Encoder ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Hardware Conditioned Policies for Multi-Robot Transfer Learning ✅ ❌ ❌ ✅ ❌ ❌ ✅ 3
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Heterogeneous Bitwidth Binarization in Convolutional Neural Networks ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Heterogeneous Multi-output Gaussian Process Prediction ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Hierarchical Graph Representation Learning with Differentiable Pooling ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
High Dimensional Linear Regression using Lattice Basis Reduction ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
HitNet: Hybrid Ternary Recurrent Neural Network ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Horizon-Independent Minimax Linear Regression ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
How Does Batch Normalization Help Optimization? ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
How Many Samples are Needed to Estimate a Convolutional Neural Network? ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery? ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
How to Start Training: The Effect of Initialization and Architecture ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
How to tell when a clustering is (approximately) correct using convex relaxations ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Human-in-the-Loop Interpretability Prior ❌ ❌ ✅ ✅ ❌ ❌ ❌ 2
Hunting for Discriminatory Proxies in Linear Regression Models ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Hybrid Knowledge Routed Modules for Large-scale Object Detection ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Hybrid-MST: A Hybrid Active Sampling Strategy for Pairwise Preference Aggregation ✅ ✅ ✅ ❌ ✅ ✅ ❌ 5
Hyperbolic Neural Networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Identification and Estimation of Causal Effects from Dependent Data ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Image Inpainting via Generative Multi-column Convolutional Neural Networks ❌ ❌ ✅ ✅ ✅ ✅ ✅ 5
Image-to-image translation for cross-domain disentanglement ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Implicit Bias of Gradient Descent on Linear Convolutional Networks ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Implicit Probabilistic Integrators for ODEs ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Implicit Reparameterization Gradients ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Importance Weighting and Variational Inference ✅ ❌ ✅ ❌ ❌ ✅ ✅ 4
Improved Algorithms for Collaborative PAC Learning ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Improved Expressivity Through Dendritic Neural Networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Improved Network Robustness with Adversary Critic ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Improving Explorability in Variational Inference with Annealed Variational Objectives ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Improving Neural Program Synthesis with Inferred Execution Traces ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Improving Online Algorithms via ML Predictions ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Improving Simple Models with Confidence Profiles ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Incorporating Context into Language Encoding Models for fMRI ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Inequity aversion improves cooperation in intertemporal social dilemmas ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Inexact trust-region algorithms on Riemannian manifolds ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Inferring Latent Velocities from Weather Radar Data using Gaussian Processes ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Inferring Networks From Random Walk-Based Node Similarities ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Infinite-Horizon Gaussian Processes ✅ ✅ ✅ ❌ ✅ ✅ ✅ 6
Information Constraints on Auto-Encoding Variational Bayes ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Information-theoretic Limits for Community Detection in Network Models ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Informative Features for Model Comparison ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Insights on representational similarity in neural networks with canonical correlation ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Integrated accounts of behavioral and neuroimaging data using flexible recurrent neural network models ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Interactive Structure Learning with Structural Query-by-Committee ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections ✅ ❌ ✅ ✅ ✅ ✅ ✅ 6
IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Invariant Representations without Adversarial Training ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Invertibility of Convolutional Generative Networks from Partial Measurements ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Is Q-Learning Provably Efficient? ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Isolating Sources of Disentanglement in Variational Autoencoders ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Iterative Value-Aware Model Learning ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
Joint Autoregressive and Hierarchical Priors for Learned Image Compression ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
KDGAN: Knowledge Distillation with Generative Adversarial Networks ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
KONG: Kernels for ordered-neighborhood graphs ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
Kalman Normalization: Normalizing Internal Representations Across Network Layers ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Knowledge Distillation by On-the-Fly Native Ensemble ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
L4: Practical loss-based stepsize adaptation for deep learning ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
LF-Net: Learning Local Features from Images ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Large Margin Deep Networks for Classification ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Large-Scale Stochastic Sampling from the Probability Simplex ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Latent Alignment and Variational Attention ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Latent Gaussian Activity Propagation: Using Smoothness and Structure to Separate and Localize Sounds in Large Noisy Environments ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Learning Abstract Options ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Learning Attentional Communication for Multi-Agent Cooperation ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Learning Attractor Dynamics for Generative Memory ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Learning Beam Search Policies via Imitation Learning ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Learning Compressed Transforms with Low Displacement Rank ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Learning Concave Conditional Likelihood Models for Improved Analysis of Tandem Mass Spectra ❌ ❌ ✅ ❌ ✅ ✅ ✅ 4
Learning Conditioned Graph Structures for Interpretable Visual Question Answering ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Learning Confidence Sets using Support Vector Machines ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Learning Deep Disentangled Embeddings With the F-Statistic Loss ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Learning Disentangled Joint Continuous and Discrete Representations ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Bounds ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Learning Hierarchical Semantic Image Manipulation through Structured Representations ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Learning Invariances using the Marginal Likelihood ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Learning Latent Subspaces in Variational Autoencoders ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Learning Loop Invariants for Program Verification ❌ ✅ ✅ ❌ ✅ ❌ ❌ 3
Learning Optimal Reserve Price against Non-myopic Bidders ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Learning Others' Intentional Models in Multi-Agent Settings Using Interactive POMDPs ✅ ❌ ❌ ❌ ❌ ✅ ❌ 2
Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Learning Plannable Representations with Causal InfoGAN ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Learning SMaLL Predictors ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Learning Safe Policies with Expert Guidance ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Learning Task Specifications from Demonstrations ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Learning Temporal Point Processes via Reinforcement Learning ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Learning To Learn Around A Common Mean ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Learning Versatile Filters for Efficient Convolutional Neural Networks ❌ ✅ ✅ ✅ ❌ ❌ ❌ 3
Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization ✅ ❌ ✅ ✅ ✅ ❌ ✅ 5
Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Learning a latent manifold of odor representations from neural responses in piriform cortex ❌ ❌ ❌ ✅ ❌ ❌ ✅ 2
Learning and Inference in Hilbert Space with Quantum Graphical Models ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Learning and Testing Causal Models with Interventions ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Learning convex bounds for linear quadratic control policy synthesis ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Learning convex polytopes with margin ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Learning filter widths of spectral decompositions with wavelets ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Learning from Group Comparisons: Exploiting Higher Order Interactions ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Learning from discriminative feature feedback ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Learning in Games with Lossy Feedback ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Learning latent variable structured prediction models with Gaussian perturbations ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Learning long-range spatial dependencies with horizontal gated recurrent units ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Learning semantic similarity in a continuous space ❌ ✅ ✅ ❌ ✅ ✅ ✅ 5
Learning sparse neural networks via sensitivity-driven regularization ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Learning to Decompose and Disentangle Representations for Video Prediction ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Learning to Exploit Stability for 3D Scene Parsing ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Learning to Infer Graphics Programs from Hand-Drawn Images ❌ ✅ ✅ ❌ ✅ ❌ ❌ 3
Learning to Multitask ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Learning to Navigate in Cities Without a Map ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Learning to Optimize Tensor Programs ✅ ✅ ✅ ❌ ✅ ✅ ✅ 6
Learning to Play With Intrinsically-Motivated, Self-Aware Agents ❌ ❌ ❌ ✅ ❌ ❌ ✅ 2
Learning to Reason with Third Order Tensor Products ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Learning to Reconstruct Shapes from Unseen Classes ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Learning to Repair Software Vulnerabilities with Generative Adversarial Networks ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Learning to Share and Hide Intentions using Information Regularization ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Learning to Solve SMT Formulas ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Learning to Specialize with Knowledge Distillation for Visual Question Answering ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Learning to Teach with Dynamic Loss Functions ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Learning towards Minimum Hyperspherical Energy ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Learning with SGD and Random Features ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Learning without the Phase: Regularized PhaseMax Achieves Optimal Sample Complexity ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Legendre Decomposition for Tensors ✅ ✅ ✅ ❌ ✅ ✅ ✅ 6
Leveraged volume sampling for linear regression ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Leveraging the Exact Likelihood of Deep Latent Variable Models ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Lifelong Inverse Reinforcement Learning ✅ ❌ ❌ ❌ ❌ ✅ ✅ 3
Lifted Weighted Mini-Bucket ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Limited Memory Kelley's Method Converges for Composite Convex and Submodular Objectives ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Link Prediction Based on Graph Neural Networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
LinkNet: Relational Embedding for Scene Graph ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Lipschitz regularity of deep neural networks: analysis and efficient estimation ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Local Differential Privacy for Evolving Data ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Long short-term memory and Learning-to-learn in networks of spiking neurons ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Loss Functions for Multiset Prediction ❌ ❌ ✅ ✅ ❌ ❌ ❌ 2
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Low-Rank Tucker Decomposition of Large Tensors Using TensorSketch ✅ ✅ ❌ ❌ ✅ ✅ ✅ 5
Low-rank Interaction with Sparse Additive Effects Model for Large Data Frames ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search ❌ ✅ ✅ ✅ ❌ ❌ ❌ 3
MULAN: A Blind and Off-Grid Method for Multichannel Echo Retrieval ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Mallows Models for Top-k Lists ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Manifold Structured Prediction ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Masking: A New Perspective of Noisy Supervision ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Maximizing Induced Cardinality Under a Determinantal Point Process ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Maximizing acquisition functions for Bayesian optimization ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Maximum Causal Tsallis Entropy Imitation Learning ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Maximum-Entropy Fine Grained Classification ❌ ❌ ✅ ❌ ✅ ❌ ❌ 2
Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence Issues ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Mean-field theory of graph neural networks in graph partitioning ❌ ❌ ❌ ✅ ❌ ✅ ✅ 3
Measures of distortion for machine learning ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Memory Replay GANs: Learning to Generate New Categories without Forgetting ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Mental Sampling in Multimodal Representations ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Mesh-TensorFlow: Deep Learning for Supercomputers ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
Meta-Gradient Reinforcement Learning ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Meta-Learning MCMC Proposals ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Meta-Reinforcement Learning of Structured Exploration Strategies ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
MetaAnchor: Learning to Detect Objects with Customized Anchors ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
MetaGAN: An Adversarial Approach to Few-Shot Learning ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
MetaReg: Towards Domain Generalization using Meta-Regularization ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operators ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare ❌ ✅ ❌ ✅ ❌ ❌ ✅ 3
Middle-Out Decoding ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Minimax Estimation of Neural Net Distance ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Minimax Statistical Learning with Wasserstein distances ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Mirrored Langevin Dynamics ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
MixLasso: Generalized Mixed Regression via Convex Atomic-Norm Regularization ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Mixture Matrix Completion ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Model Agnostic Supervised Local Explanations ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Model-Agnostic Private Learning ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Model-based targeted dimensionality reduction for neuronal population data ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Modeling Dynamic Missingness of Implicit Feedback for Recommendation ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Modelling and unsupervised learning of symmetric deformable object categories ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Modelling sparsity, heterogeneity, reciprocity and community structure in temporal interaction data ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Modern Neural Networks Generalize on Small Data Sets ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Modular Networks: Learning to Decompose Neural Computation ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Monte-Carlo Tree Search for Constrained POMDPs ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Moonshine: Distilling with Cheap Convolutions ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Multi-Agent Generative Adversarial Imitation Learning ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Multi-Class Learning: From Theory to Algorithm ✅ ❌ ✅ ✅ ❌ ✅ ✅ 5
Multi-Layered Gradient Boosting Decision Trees ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Multi-Task Learning as Multi-Objective Optimization ✅ ❌ ✅ ✅ ✅ ❌ ❌ 4
Multi-Task Zipping via Layer-wise Neuron Sharing ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation ❌ ✅ ✅ ✅ ✅ ❌ ❌ 4
Multi-armed Bandits with Compensation ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Multi-domain Causal Structure Learning in Linear Systems ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Multi-objective Maximization of Monotone Submodular Functions with Cardinality Constraint ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Multimodal Generative Models for Scalable Weakly-Supervised Learning ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Multiple-Step Greedy Policies in Approximate and Online Reinforcement Learning ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Multiplicative Weights Updates with Constant Step-Size in Graphical Constant-Sum Games ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Multitask Boosting for Survival Analysis with Competing Risks ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Multivariate Time Series Imputation with Generative Adversarial Networks ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
NEON2: Finding Local Minima via First-Order Oracles ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Natasha 2: Faster Non-Convex Optimization Than SGD ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Neighbourhood Consensus Networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Neural Architecture Optimization ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
Neural Architecture Search with Bayesian Optimisation and Optimal Transport ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Neural Arithmetic Logic Units ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Neural Code Comprehension: A Learnable Representation of Code Semantics ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Neural Edit Operations for Biological Sequences ✅ ❌ ✅ ❌ ❌ ✅ ✅ 4
Neural Guided Constraint Logic Programming for Program Synthesis ❌ ✅ ❌ ❌ ✅ ❌ ✅ 3
Neural Interaction Transparency (NIT): Disentangling Learned Interactions for Improved Interpretability ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Neural Nearest Neighbors Networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Neural Networks Trained to Solve Differential Equations Learn General Representations ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Neural Ordinary Differential Equations ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Neural Proximal Gradient Descent for Compressive Imaging ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Neural Tangent Kernel: Convergence and Generalization in Neural Networks ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Neural Voice Cloning with a Few Samples ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Non-Adversarial Mapping with VAEs ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Non-Ergodic Alternating Proximal Augmented Lagrangian Algorithms with Optimal Rates ✅ ❌ ❌ ❌ ✅ ✅ ✅ 4
Non-Local Recurrent Network for Image Restoration ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Non-delusional Q-learning and value-iteration ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Non-metric Similarity Graphs for Maximum Inner Product Search ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Non-monotone Submodular Maximization in Exponentially Fewer Iterations ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Nonlocal Neural Networks, Nonlocal Diffusion and Nonlocal Modeling ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Nonparametric Bayesian Lomax delegate racing for survival analysis with competing risks ❌ ✅ ✅ ❌ ❌ ✅ ❌ 3
Nonparametric Density Estimation under Adversarial Losses ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Nonparametric learning from Bayesian models with randomized objective functions ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Norm matters: efficient and accurate normalization schemes in deep networks ❌ ✅ ✅ ❌ ✅ ❌ ❌ 3
Norm-Ranging LSH for Maximum Inner Product Search ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Object-Oriented Dynamics Predictor ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Objective and efficient inference for couplings in neuronal networks ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Occam's razor is insufficient to infer the preferences of irrational agents ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
On Binary Classification in Extreme Regions ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
On Controllable Sparse Alternatives to Softmax ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
On Coresets for Logistic Regression ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
On Fast Leverage Score Sampling and Optimal Learning ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
On GANs and GMMs ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
On Learning Intrinsic Rewards for Policy Gradient Methods ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
On Learning Markov Chains ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
On Markov Chain Gradient Descent ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
On Misinformation Containment in Online Social Networks ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
On Neuronal Capacity ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
On Oracle-Efficient PAC RL with Rich Observations ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
On gradient regularizers for MMD GANs ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
On preserving non-discrimination when combining expert advice ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
On the Convergence and Robustness of Training GANs with Regularized Optimal Transport ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
On the Dimensionality of Word Embedding ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
On the Local Hessian in Back-propagation ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
On the Local Minima of the Empirical Risk ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
One-Shot Unsupervised Cross Domain Translation ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Online Adaptive Methods, Universality and Acceleration ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Online Improper Learning with an Approximation Oracle ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Online Learning of Quantum States ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Online Learning with an Unknown Fairness Metric ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Online Reciprocal Recommendation with Theoretical Performance Guarantees ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Online Robust Policy Learning in the Presence of Unknown Adversaries ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks ✅ ❌ ✅ ✅ ✅ ❌ ✅ 5
Online Structured Laplace Approximations for Overcoming Catastrophic Forgetting ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Online convex optimization for cumulative constraints ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Optimal Algorithms for Non-Smooth Distributed Optimization in Networks ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Optimal Subsampling with Influence Functions ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Optimistic optimization of a Brownian ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Optimization for Approximate Submodularity ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Optimization of Smooth Functions with Noisy Observations: Local Minimax Rates ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Optimization over Continuous and Multi-dimensional Decisions with Observational Data ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Orthogonally Decoupled Variational Gaussian Processes ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Out-of-Distribution Detection using Multiple Semantic Label Representations ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Overcoming Language Priors in Visual Question Answering with Adversarial Regularization ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Overlapping Clustering Models, and One (class) SVM to Bind Them All ✅ ❌ ✅ ❌ ❌ ✅ ✅ 4
PAC-Bayes Tree: weighted subtrees with guarantees ✅ ❌ ✅ ✅ ❌ ❌ ❌ 3
PAC-Bayes bounds for stable algorithms with instance-dependent priors ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
PAC-learning in the presence of adversaries ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
PCA of high dimensional random walks with comparison to neural network training ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
PacGAN: The power of two samples in generative adversarial networks ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Paraphrasing Complex Network: Network Compression via Factor Transfer ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Parsimonious Bayesian deep networks ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential Learning ❌ ❌ ❌ ✅ ❌ ❌ ✅ 2
Partially-Supervised Image Captioning ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
Pelee: A Real-Time Object Detection System on Mobile Devices ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagrams ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Phase Retrieval Under a Generative Prior ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training ✅ ❌ ✅ ✅ ✅ ✅ ✅ 6
Playing hard exploration games by watching YouTube ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Point process latent variable models of larval zebrafish behavior ❌ ❌ ❌ ✅ ❌ ❌ ✅ 2
PointCNN: Convolution On X-Transformed Points ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Policy Optimization via Importance Sampling ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Policy Regret in Repeated Games ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Porcupine Neural Networks: Approximating Neural Network Landscapes ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Post: Device Placement with Cross-Entropy Minimization and Proximal Policy Optimization ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Posterior Concentration for Sparse Deep Learning ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Power-law efficient neural codes provide general link between perceptual bias and discriminability ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Practical Methods for Graph Two-Sample Testing ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Practical exact algorithm for trembling-hand equilibrium refinements in games ❌ ❌ ❌ ❌ ❌ ✅ ✅ 2
Precision and Recall for Time Series ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Predictive Approximate Bayesian Computation via Saddle Points ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Predictive Uncertainty Estimation via Prior Networks ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Preference Based Adaptation for Learning Objectives ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Probabilistic Matrix Factorization for Automated Machine Learning ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Probabilistic Model-Agnostic Meta-Learning ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
Probabilistic Neural Programmed Networks for Scene Generation ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Processing of missing data by neural networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Provable Gaussian Embedding with One Observation ❌ ❌ ❌ ✅ ❌ ❌ ✅ 2
Provable Variational Inference for Constrained Log-Submodular Models ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Provably Correct Automatic Sub-Differentiation for Qualified Programs ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Proximal Graphical Event Models ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Proximal SCOPE for Distributed Sparse Learning ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Q-learning with Nearest Neighbors ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Quadratic Decomposable Submodular Function Minimization ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Quadrature-based features for kernel approximation ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Quantifying Learning Guarantees for Convex but Inconsistent Surrogates ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Query Complexity of Bayesian Private Learning ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Query K-means Clustering and the Double Dixie Cup Problem ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis ✅ ❌ ❌ ✅ ❌ ❌ ✅ 3
Random Feature Stein Discrepancies ❌ ✅ ❌ ❌ ❌ ❌ ✅ 2
Randomized Prior Functions for Deep Reinforcement Learning ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Re-evaluating evaluation ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
Realistic Evaluation of Deep Semi-Supervised Learning Algorithms ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Rectangular Bounding Process ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Recurrent Relational Networks ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Recurrent Transformer Networks for Semantic Correspondence ❌ ❌ ✅ ✅ ❌ ❌ ❌ 2
Recurrent World Models Facilitate Policy Evolution ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Recurrently Controlled Recurrent Networks ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Reducing Network Agnostophobia ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Regret Bounds for Online Portfolio Selection with a Cardinality Constraint ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Regularization Learning Networks: Deep Learning for Tabular Datasets ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Regularizing by the Variance of the Activations' Sample-Variances ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Reinforced Continual Learning ✅ ❌ ✅ ❌ ✅ ❌ ❌ 3
Reinforcement Learning for Solving the Vehicle Routing Problem ❌ ❌ ❌ ❌ ✅ ❌ ✅ 2
Reinforcement Learning of Theorem Proving ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Relating Leverage Scores and Density using Regularized Christoffel Functions ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Relational recurrent neural networks ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Removing Hidden Confounding by Experimental Grounding ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Removing the Feature Correlation Effect of Multiplicative Noise ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
RenderNet: A deep convolutional network for differentiable rendering from 3D shapes ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Reparameterization Gradient for Non-differentiable Models ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Representation Balancing MDPs for Off-policy Policy Evaluation ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Representation Learning for Treatment Effect Estimation from Observational Data ❌ ✅ ✅ ❌ ✅ ❌ ❌ 3
Representation Learning of Compositional Data ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Representer Point Selection for Explaining Deep Neural Networks ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
ResNet with one-neuron hidden layers is a Universal Approximator ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
RetGK: Graph Kernels based on Return Probabilities of Random Walks ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Reversible Recurrent Neural Networks ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Revisiting $(\epsilon, \gamma, \tau)$-similarity learning for domain adaptation ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Revisiting Decomposable Submodular Function Minimization with Incidence Relations ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Reward learning from human preferences and demonstrations in Atari ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Ridge Regression and Provable Deterministic Ridge Leverage Score Sampling ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias ❌ ❌ ❌ ❌ ✅ ❌ ✅ 2
Robust Detection of Adversarial Attacks by Modeling the Intrinsic Properties of Deep Neural Networks ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Robust Hypothesis Testing Using Wasserstein Uncertainty Sets ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Robust Learning of Fixed-Structure Bayesian Networks ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Robust Subspace Approximation in a Stream ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Robustness of conditional GANs to noisy labels ❌ ✅ ✅ ❌ ✅ ❌ ❌ 3
SEGA: Variance Reduction via Gradient Sketching ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
SING: Symbol-to-Instrument Neural Generator ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
SLAYER: Spike Layer Error Reassignment in Time ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
SNIPER: Efficient Multi-Scale Training ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Safe Active Learning for Time-Series Modeling with Gaussian Processes ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion ❌ ✅ ✅ ❌ ✅ ❌ ❌ 3
Sanity Checks for Saliency Maps ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Scalable Coordinated Exploration in Concurrent Reinforcement Learning ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation ✅ ❌ ✅ ❌ ❌ ✅ ✅ 4
Scalable Hyperparameter Transfer Learning ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Scalable Laplacian K-modes ✅ ✅ ✅ ✅ ✅ ❌ ✅ 6
Scalable Robust Matrix Factorization with Nonconvex Loss ✅ ❌ ✅ ✅ ✅ ❌ ✅ 5
Scalable methods for 8-bit training of neural networks ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Scalar Posterior Sampling with Applications ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Scaling Gaussian Process Regression with Derivatives ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
Scaling provable adversarial defenses ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Scaling the Poisson GLM to massive neural datasets through polynomial approximations ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
See and Think: Disentangling Semantic Scene Completion ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Self-Erasing Network for Integral Object Attention ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Self-Supervised Generation of Spatial Audio for 360° Video ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Semi-Supervised Learning with Declaratively Specified Entropy Constraints ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Semi-crowdsourced Clustering with Deep Generative Models ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Semidefinite relaxations for certifying robustness to adversarial examples ❌ ✅ ✅ ❌ ✅ ❌ ✅ 4
Sequence-to-Segment Networks for Segment Detection ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Sequential Context Encoding for Duplicate Removal ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Sharp Bounds for Generalized Uniformity Testing ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Sigsoftmax: Reanalysis of the Softmax Bottleneck ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
SimplE Embedding for Link Prediction in Knowledge Graphs ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Simple random search of static linear policies is competitive for reinforcement learning ✅ ❌ ✅ ❌ ❌ ✅ ✅ 4
Simple, Distributed, and Accelerated Probabilistic Programming ✅ ✅ ✅ ❌ ✅ ✅ ✅ 6
Single-Agent Policy Tree Search With Guarantees ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Size-Noise Tradeoffs in Generative Networks ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Sketching Method for Large Scale Combinatorial Inference ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Smoothed analysis of the low-rank approach for smooth semidefinite programs ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Snap ML: A Hierarchical Framework for Machine Learning ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Solving Large Sequential Games with the Excessive Gap Technique ✅ ❌ ❌ ❌ ✅ ❌ ✅ 3
Solving Non-smooth Constrained Programs with Lower Complexity than $\mathcal{O}(1/\varepsilon)$: A Primal-Dual Homotopy Smoothing Approach ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Sparse DNNs with Improved Adversarial Robustness ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Sparse PCA from Sparse Linear Regression ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Sparsified SGD with Memory ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Speaker-Follower Models for Vision-and-Language Navigation ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Spectral Filtering for General Linear Dynamical Systems ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Spectral Signatures in Backdoor Attacks ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
SplineNets: Continuous Neural Decision Graphs ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Statistical and Computational Trade-Offs in Kernel K-Means ✅ ❌ ✅ ✅ ✅ ❌ ✅ 5
Statistical mechanics of low-rank tensor decomposition ❌ ✅ ❌ ❌ ❌ ❌ ✅ 2
Stein Variational Gradient Descent as Moment Matching ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Step Size Matters in Deep Learning ❌ ✅ ❌ ❌ ❌ ❌ ✅ 2
Stimulus domain transfer in recurrent models for large scale cortical population prediction on video ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Stochastic Chebyshev Gradient Descent for Spectral Optimization ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
Stochastic Composite Mirror Descent: Optimal Bounds with High Probabilities ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Stochastic Cubic Regularization for Fast Nonconvex Optimization ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Stochastic Expectation Maximization with Variance Reduction ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Stochastic Nested Variance Reduction for Nonconvex Optimization ✅ ❌ ✅ ❌ ✅ ✅ ✅ 5
Stochastic Nonparametric Event-Tensor Decomposition ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Stochastic Spectral and Conjugate Descent Methods ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Streamlining Variational Inference for Constraint Satisfaction Problems ✅ ✅ ❌ ✅ ❌ ❌ ✅ 4
Structural Causal Bandits: Where to Intervene? ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
Structure-Aware Convolutional Neural Networks ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Structured Local Minima in Sparse Blind Deconvolution ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Sublinear Time Low-Rank Approximation of Distance Matrices ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Submodular Field Grammars: Representation, Inference, and Application to Image Parsing ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Submodular Maximization via Gradient Ascent: The Case of Deep Submodular Functions ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Supervised autoencoders: Improving generalization performance with unsupervised regularizers ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Supervising Unsupervised Learning ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Symbolic Graph Reasoning Meets Convolutions ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Synaptic Strength For Convolutional Neural Network ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Synthesized Policies for Transfer and Adaptation across Tasks and Environments ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
TADAM: Task dependent adaptive metric for improved few-shot learning ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
TETRIS: TilE-matching the TRemendous Irregular Sparsity ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming ❌ ✅ ❌ ❌ ✅ ✅ ✅ 4
Task-Driven Convolutional Recurrent Models of the Visual System ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Teaching Inverse Reinforcement Learners via Features and Demonstrations ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Temporal Regularization for Markov Decision Process ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Temporal alignment and latent Gaussian process factor inference in population spike trains ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Testing for Families of Distributions via the Fourier Transform ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
The Cluster Description Problem - Complexity Results, Formulations and Approximations ✅ ✅ ❌ ❌ ✅ ❌ ✅ 4
The Convergence of Sparsified Gradient Methods ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
The Description Length of Deep Learning models ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
The Effect of Network Width on the Performance of Large-batch Training ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
The Everlasting Database: Statistical Validity at a Fair Price ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
The Global Anchor Method for Quantifying Linguistic Shifts and Domain Adaptation ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
The Importance of Sampling inMeta-Reinforcement Learning ✅ ✅ ❌ ❌ ❌ ❌ ✅ 3
The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
The Limits of Post-Selection Generalization ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
The Lingering of Gradients: How to Reuse Gradients Over Time ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-Optimal ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
The Physical Systems Behind Optimization Algorithms ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
The Price of Fair PCA: One Extra dimension ✅ ❌ ✅ ❌ ❌ ❌ ❌ 2
The Price of Privacy for Low-rank Factorization ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
The Sample Complexity of Semi-Supervised Learning with Nonparametric Mixture Models ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
The Sparse Manifold Transform ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
The challenge of realistic music generation: modelling raw audio at scale ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
The committee machine: Computational to statistical gaps in learning a two-layers neural network ✅ ✅ ❌ ❌ ✅ ❌ ❌ 3
The emergence of multiple retinal cell types through efficient coding of natural movies ❌ ✅ ❌ ❌ ❌ ❌ ✅ 2
The promises and pitfalls of Stochastic Gradient Langevin Dynamics ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
The streaming rollout of deep networks - towards fully model-parallel execution ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Theoretical guarantees for EM under misspecified Gaussian mixture models ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Third-order Smoothness Helps: Faster Stochastic Optimization Algorithms for Finding Local Minima ✅ ❌ ✅ ❌ ✅ ✅ ✅ 5
Thwarting Adversarial Examples: An $L_0$-Robust Sparse Fourier Transform ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Tight Bounds for Collaborative PAC Learning via Multiplicative Weights ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
To Trust Or Not To Trust A Classifier ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Toddler-Inspired Visual Object Learning ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
TopRank: A practical algorithm for online stochastic ranking ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Topkapi: Parallel and Fast Sketches for Finding Top-K Frequent Elements ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5
Total stochastic gradient algorithms and applications in reinforcement learning ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Towards Deep Conversational Recommendations ❌ ❌ ✅ ✅ ❌ ❌ ❌ 2
Towards Robust Detection of Adversarial Examples ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Towards Robust Interpretability with Self-Explaining Neural Networks ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Towards Text Generation with Adversarially Learned Neural Outlines ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation ✅ ❌ ✅ ✅ ❌ ❌ ❌ 3
Trading robust representations for sample complexity through self-supervised visual experience ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Training DNNs with Hybrid Block Floating Point ❌ ❌ ✅ ❌ ✅ ❌ ❌ 2
Training Deep Models Faster with Robust, Approximate Importance Sampling ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Training Deep Neural Networks with 8-bit Floating Point Numbers ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Training Neural Networks Using Features Replay ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Training deep learning based denoisers without ground truth data ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
Trajectory Convolution for Action Recognition ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Transfer Learning with Neural AutoML ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Transfer of Deep Reactive Policies for MDP Planning ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Transfer of Value Functions via Variational Methods ✅ ❌ ❌ ✅ ✅ ❌ ✅ 4
Tree-to-tree Neural Networks for Program Translation ❌ ❌ ❌ ✅ ❌ ❌ ❌ 1
Turbo Learning for CaptionBot and DrawingBot ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Uncertainty-Aware Attention for Reliable Interpretation and Prediction ❌ ✅ ✅ ✅ ❌ ❌ ❌ 3
Understanding Batch Normalization ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Understanding Regularized Spectral Clustering via Graph Conductance ❌ ❌ ✅ ❌ ❌ ✅ ✅ 3
Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Uniform Convergence of Gradients for Non-Convex Learning and Optimization ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Universal Growth in Production Economies ❌ ❌ ❌ ❌ ❌ ❌ ❌ 0
Unorganized Malicious Attacks Detection ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Unsupervised Adversarial Invariance ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Unsupervised Attention-guided Image-to-Image Translation ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Unsupervised Depth Estimation, 3D Face Rotation and Replacement ❌ ❌ ✅ ✅ ❌ ❌ ❌ 2
Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Unsupervised Learning of Artistic Styles with Archetypal Style Analysis ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Unsupervised Learning of Object Landmarks through Conditional Image Generation ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Unsupervised Learning of Shape and Pose with Differentiable Point Clouds ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Unsupervised Learning of View-invariant Action Representations ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Unsupervised Text Style Transfer using Language Models as Discriminators ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Unsupervised Video Object Segmentation for Deep Reinforcement Learning ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Uplift Modeling from Separate Labels ❌ ❌ ✅ ✅ ❌ ❌ ✅ 3
Using Large Ensembles of Control Variates for Variational Inference ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise ✅ ✅ ✅ ✅ ❌ ❌ ✅ 5
Variance-Reduced Stochastic Gradient Descent on Streaming Data ✅ ❌ ✅ ❌ ❌ ❌ ✅ 3
Variational Bayesian Monte Carlo ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Variational Inference with Tail-adaptive f-Divergence ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Variational Learning on Aggregate Outputs with Gaussian Processes ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Variational Memory Encoder-Decoder ✅ ✅ ✅ ✅ ❌ ❌ ❌ 4
Variational PDEs for Acceleration on Manifolds and Application to Diffeomorphisms ❌ ❌ ❌ ❌ ❌ ❌ ✅ 1
Verifiable Reinforcement Learning via Policy Extraction ✅ ❌ ✅ ❌ ✅ ❌ ✅ 4
Video Prediction via Selective Sampling ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
Video-to-Video Synthesis ❌ ✅ ✅ ✅ ✅ ❌ ✅ 5
VideoCapsuleNet: A Simplified Network for Action Detection ❌ ❌ ✅ ✅ ✅ ❌ ✅ 4
Virtual Class Enhanced Discriminative Embedding Learning ❌ ❌ ✅ ❌ ✅ ❌ ✅ 3
Visual Memory for Robust Path Following ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Visual Object Networks: Image Generation with Disentangled 3D Representations ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Visual Reinforcement Learning with Imagined Goals ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Visualizing the Loss Landscape of Neural Nets ❌ ✅ ✅ ❌ ❌ ❌ ✅ 3
Wasserstein Distributionally Robust Kalman Filtering ✅ ✅ ❌ ❌ ✅ ❌ ✅ 4
Wasserstein Variational Inference ✅ ❌ ✅ ✅ ❌ ❌ ✅ 4
Watch Your Step: Learning Node Embeddings via Graph Attention ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
Wavelet regression and additive models for irregularly spaced data ❌ ❌ ✅ ✅ ❌ ✅ ✅ 4
Weakly Supervised Dense Event Captioning in Videos ❌ ✅ ✅ ✅ ❌ ✅ ✅ 5
When do random forests fail? ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior ❌ ✅ ✅ ❌ ❌ ❌ ❌ 2
Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients? ❌ ❌ ✅ ❌ ❌ ❌ ❌ 1
Why Is My Classifier Discriminatory? ❌ ❌ ✅ ✅ ❌ ❌ ❌ 2
Why so gloomy? A Bayesian explanation of human pessimism bias in the multi-armed bandit task ❌ ❌ ❌ ✅ ❌ ❌ ✅ 2
With Friends Like These, Who Needs Adversaries? ✅ ✅ ✅ ❌ ❌ ❌ ❌ 3
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning ✅ ❌ ❌ ❌ ❌ ❌ ✅ 2
Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization ✅ ✅ ✅ ❌ ❌ ❌ ✅ 4
Zeroth-order (Non)-Convex Stochastic Optimization via Conditional Gradient and Gradient Updates ✅ ❌ ❌ ❌ ❌ ❌ ❌ 1
cpSGD: Communication-efficient and differentially-private distributed SGD ❌ ❌ ✅ ❌ ❌ ❌ ✅ 2
e-SNLI: Natural Language Inference with Natural Language Explanations ❌ ✅ ✅ ✅ ❌ ❌ ✅ 4
rho-POMDPs have Lipschitz-Continuous epsilon-Optimal Value Functions ✅ ✅ ✅ ❌ ✅ ❌ ✅ 5