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) - 2015

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	2015	403	0.35	2.94	88.34%	25.0%

Search Papers

	Pseudocode	Open Source Code	Open Datasets	Dataset Splits	Hardware Specification	Software Dependencies	Experiment Setup
3D Object Proposals for Accurate Object Class Detection	❌	✅	✅	✅	❌	❌	✅	4
A Bayesian Framework for Modeling Confidence in Perceptual Decision Making	❌	❌	❌	❌	❌	❌	✅	1
A Complete Recipe for Stochastic Gradient MCMC	✅	❌	❌	❌	❌	❌	❌	1
A Convergent Gradient Descent Algorithm for Rank Minimization and Semidefinite Programming from Random Linear Measurements	✅	❌	❌	❌	✅	❌	✅	3
A Dual Augmented Block Minimization Framework for Learning with Limited Memory	✅	❌	✅	✅	✅	❌	✅	5
A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure	❌	❌	❌	✅	❌	❌	✅	2
A Gaussian Process Model of Quasar Spectral Energy Distributions	❌	❌	✅	✅	❌	❌	✅	3
A Generalization of Submodular Cover via the Diminishing Return Property on the Integer Lattice	✅	❌	✅	❌	✅	✅	✅	5
A Market Framework for Eliciting Private Data	✅	❌	❌	❌	❌	❌	❌	1
A Nonconvex Optimization Framework for Low Rank Matrix Estimation	✅	❌	❌	❌	❌	❌	✅	2
A Normative Theory of Adaptive Dimensionality Reduction in Neural Networks	❌	❌	❌	❌	❌	❌	✅	1
A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA	✅	❌	❌	❌	❌	✅	✅	3
A Recurrent Latent Variable Model for Sequential Data	❌	✅	✅	✅	❌	❌	✅	4
A Reduced-Dimension fMRI Shared Response Model	❌	❌	✅	✅	❌	❌	✅	3
A Structural Smoothing Framework For Robust Graph Comparison	✅	✅	✅	✅	❌	❌	✅	5
A Theory of Decision Making Under Dynamic Context	❌	✅	✅	❌	❌	❌	✅	3
A Tractable Approximation to Optimal Point Process Filtering: Application to Neural Encoding	❌	❌	❌	❌	❌	❌	✅	1
A Universal Catalyst for First-Order Optimization	✅	❌	✅	❌	❌	❌	✅	3
A Universal Primal-Dual Convex Optimization Framework	✅	❌	✅	❌	❌	❌	✅	3
A class of network models recoverable by spectral clustering	✅	❌	❌	❌	❌	❌	✅	2
A fast, universal algorithm to learn parametric nonlinear embeddings	❌	❌	✅	❌	❌	❌	✅	2
A hybrid sampler for Poisson-Kingman mixture models	✅	❌	✅	❌	❌	❌	❌	2
Accelerated Mirror Descent in Continuous and Discrete Time	✅	❌	❌	❌	❌	❌	✅	2
Accelerated Proximal Gradient Methods for Nonconvex Programming	✅	❌	✅	❌	✅	✅	✅	5
Action-Conditional Video Prediction using Deep Networks in Atari Games	❌	❌	❌	❌	❌	❌	✅	1
Active Learning from Weak and Strong Labelers	✅	❌	❌	❌	❌	❌	❌	1
Adaptive Low-Complexity Sequential Inference for Dirichlet Process Mixture Models	✅	❌	✅	✅	❌	❌	❌	3
Adaptive Online Learning	❌	❌	❌	❌	❌	❌	❌	0
Adaptive Primal-Dual Splitting Methods for Statistical Learning and Image Processing	✅	❌	✅	❌	❌	❌	✅	3
Adaptive Stochastic Optimization: From Sets to Paths	✅	❌	❌	❌	❌	❌	✅	2
Adversarial Prediction Games for Multivariate Losses	✅	❌	✅	✅	❌	❌	✅	4
Algorithmic Stability and Uniform Generalization	❌	❌	❌	❌	❌	❌	❌	0
Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits	✅	❌	❌	❌	❌	❌	❌	1
Alternating Minimization for Regression Problems with Vector-valued Outputs	✅	❌	❌	❌	❌	❌	❌	1
An Active Learning Framework using Sparse-Graph Codes for Sparse Polynomials and Graph Sketching	❌	❌	✅	❌	✅	❌	✅	3
Analysis of Robust PCA via Local Incoherence	❌	❌	❌	❌	❌	❌	✅	1
Anytime Influence Bounds and the Explosive Behavior of Continuous-Time Diffusion Networks	❌	❌	❌	❌	❌	❌	✅	1
Approximating Sparse PCA from Incomplete Data	✅	❌	✅	❌	❌	❌	✅	3
Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question	❌	❌	✅	✅	❌	❌	✅	3
Associative Memory via a Sparse Recovery Model	✅	❌	❌	❌	❌	❌	✅	2
Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization	✅	❌	❌	❌	❌	❌	❌	1
Asynchronous stochastic convex optimization: the noise is in the noise and SGD don't care	❌	✅	✅	❌	✅	❌	✅	4
Attention-Based Models for Speech Recognition	❌	❌	✅	✅	❌	✅	✅	4
Attractor Network Dynamics Enable Preplay and Rapid Path Planning in Maze–like Environments	❌	❌	❌	❌	❌	❌	✅	1
Automatic Variational Inference in Stan	✅	✅	✅	❌	❌	✅	✅	5
BACKSHIFT: Learning causal cyclic graphs from unknown shift interventions	✅	✅	✅	❌	❌	❌	✅	4
Backpropagation for Energy-Efficient Neuromorphic Computing	❌	❌	✅	❌	✅	❌	✅	3
Bandit Smooth Convex Optimization: Improving the Bias-Variance Tradeoff	✅	❌	❌	❌	❌	❌	❌	1
Bandits with Unobserved Confounders: A Causal Approach	✅	✅	❌	❌	❌	❌	✅	3
Barrier Frank-Wolfe for Marginal Inference	✅	✅	✅	❌	❌	❌	✅	4
Basis refinement strategies for linear value function approximation in MDPs	✅	❌	❌	❌	❌	❌	❌	1
Bayesian Active Model Selection with an Application to Automated Audiometry	❌	❌	❌	❌	❌	❌	✅	1
Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)	❌	✅	✅	✅	❌	❌	✅	4
Bayesian Optimization with Exponential Convergence	✅	✅	✅	❌	❌	❌	✅	4
Bayesian dark knowledge	✅	❌	✅	✅	❌	❌	✅	4
Beyond Convexity: Stochastic Quasi-Convex Optimization	✅	❌	✅	❌	❌	❌	✅	3
Beyond Sub-Gaussian Measurements: High-Dimensional Structured Estimation with Sub-Exponential Designs	❌	❌	❌	❌	❌	❌	✅	1
Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution	❌	❌	✅	❌	✅	❌	✅	3
Bidirectional Recurrent Neural Networks as Generative Models	❌	❌	✅	✅	❌	❌	✅	3
BinaryConnect: Training Deep Neural Networks with binary weights during propagations	✅	✅	✅	✅	❌	❌	✅	5
Biologically Inspired Dynamic Textures for Probing Motion Perception	❌	✅	❌	❌	✅	✅	✅	4
Black-box optimization of noisy functions with unknown smoothness	✅	✅	❌	❌	❌	❌	✅	3
Bounding errors of Expectation-Propagation	❌	❌	❌	❌	❌	❌	❌	0
Bounding the Cost of Search-Based Lifted Inference	✅	❌	✅	❌	❌	❌	✅	3
COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution	✅	✅	✅	❌	❌	❌	❌	3
Calibrated Structured Prediction	✅	✅	✅	✅	❌	❌	✅	5
Character-level Convolutional Networks for Text Classification	❌	❌	✅	❌	✅	✅	✅	4
Closed-form Estimators for High-dimensional Generalized Linear Models	❌	❌	❌	✅	❌	❌	✅	2
Collaborative Filtering with Graph Information: Consistency and Scalable Methods	✅	❌	✅	❌	✅	❌	✅	4
Collaboratively Learning Preferences from Ordinal Data	❌	❌	❌	❌	❌	❌	✅	1
Color Constancy by Learning to Predict Chromaticity from Luminance	❌	✅	✅	✅	✅	❌	✅	5
Column Selection via Adaptive Sampling	✅	❌	✅	❌	❌	❌	✅	3
Combinatorial Bandits Revisited	✅	❌	❌	❌	❌	❌	❌	1
Combinatorial Cascading Bandits	✅	❌	✅	❌	❌	❌	❌	2
Communication Complexity of Distributed Convex Learning and Optimization	❌	❌	❌	❌	❌	❌	❌	0
Community Detection via Measure Space Embedding	✅	❌	✅	❌	❌	❌	✅	3
Competitive Distribution Estimation: Why is Good-Turing Good	❌	❌	❌	❌	❌	❌	✅	1
Compressive spectral embedding: sidestepping the SVD	✅	✅	✅	❌	❌	❌	✅	4
Consistent Multilabel Classification	✅	❌	✅	✅	❌	❌	❌	3
Convergence Analysis of Prediction Markets via Randomized Subspace Descent	✅	❌	❌	❌	❌	❌	❌	1
Convergence Rates of Active Learning for Maximum Likelihood Estimation	✅	❌	❌	❌	❌	❌	❌	1
Convergence rates of sub-sampled Newton methods	✅	❌	✅	❌	❌	❌	❌	2
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting	❌	❌	✅	✅	✅	❌	✅	4
Convolutional Networks on Graphs for Learning Molecular Fingerprints	✅	✅	✅	❌	❌	❌	✅	4
Convolutional Neural Networks with Intra-Layer Recurrent Connections for Scene Labeling	❌	❌	✅	✅	✅	❌	✅	4
Convolutional spike-triggered covariance analysis for neural subunit models	❌	❌	✅	❌	❌	❌	✅	2
Copeland Dueling Bandits	✅	✅	✅	❌	❌	❌	❌	3
Copula variational inference	✅	❌	✅	❌	❌	❌	✅	3
Cornering Stationary and Restless Mixing Bandits with Remix-UCB	✅	❌	❌	❌	❌	❌	❌	1
Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling	✅	❌	✅	❌	❌	❌	✅	3
Cross-Domain Matching for Bag-of-Words Data via Kernel Embeddings of Latent Distributions	❌	❌	❌	✅	❌	❌	✅	2
Data Generation as Sequential Decision Making	✅	✅	✅	❌	❌	❌	✅	4
Decomposition Bounds for Marginal MAP	✅	❌	✅	❌	❌	❌	✅	3
Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation	❌	❌	✅	✅	✅	❌	✅	4
Deep Convolutional Inverse Graphics Network	❌	❌	✅	✅	❌	❌	✅	3
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks	❌	✅	✅	❌	❌	❌	✅	3
Deep Knowledge Tracing	❌	✅	✅	✅	❌	❌	✅	4
Deep Poisson Factor Modeling	❌	❌	✅	❌	❌	❌	✅	2
Deep Temporal Sigmoid Belief Networks for Sequence Modeling	❌	✅	✅	❌	❌	❌	✅	3
Deep Visual Analogy-Making	✅	❌	✅	✅	✅	❌	✅	5
Deep learning with Elastic Averaging SGD	✅	✅	✅	❌	✅	❌	✅	5
Deeply Learning the Messages in Message Passing Inference	❌	❌	✅	✅	❌	❌	✅	3
Dependent Multinomial Models Made Easy: Stick-Breaking with the Polya-gamma Augmentation	❌	✅	✅	❌	❌	❌	❌	2
Differentially Private Learning of Structured Discrete Distributions	✅	❌	✅	❌	✅	✅	✅	5
Differentially private subspace clustering	✅	❌	✅	❌	❌	❌	✅	3
Discrete Rényi Classifiers	✅	❌	✅	❌	❌	❌	✅	3
Discriminative Robust Transformation Learning	✅	❌	✅	❌	❌	❌	✅	3
Distributed Submodular Cover: Succinctly Summarizing Massive Data	✅	❌	✅	❌	✅	❌	✅	4
Distributionally Robust Logistic Regression	❌	❌	✅	❌	✅	❌	✅	3
Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing	✅	❌	✅	❌	❌	❌	✅	3
Efficient Compressive Phase Retrieval with Constrained Sensing Vectors	✅	❌	❌	❌	❌	❌	✅	2
Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets	✅	✅	✅	❌	✅	❌	✅	5
Efficient Learning by Directed Acyclic Graph For Resource Constrained Prediction	✅	❌	✅	✅	❌	❌	✅	4
Efficient Learning of Continuous-Time Hidden Markov Models for Disease Progression	✅	❌	✅	❌	❌	❌	✅	3
Efficient Non-greedy Optimization of Decision Trees	✅	❌	✅	✅	❌	❌	✅	4
Efficient Output Kernel Learning for Multiple Tasks	✅	❌	✅	✅	❌	❌	❌	3
Efficient Thompson Sampling for Online Matrix-Factorization Recommendation	✅	❌	✅	❌	❌	❌	✅	3
Efficient and Parsimonious Agnostic Active Learning	✅	❌	❌	❌	❌	❌	❌	1
Efficient and Robust Automated Machine Learning	✅	✅	✅	✅	❌	❌	✅	5
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images	❌	✅	❌	❌	❌	❌	✅	2
Embedding Inference for Structured Multilabel Prediction	❌	❌	✅	❌	❌	❌	✅	2
Empirical Localization of Homogeneous Divergences on Discrete Sample Spaces	❌	❌	❌	❌	❌	✅	✅	2
End-To-End Memory Networks	❌	✅	✅	✅	❌	❌	✅	4
End-to-end Learning of LDA by Mirror-Descent Back Propagation over a Deep Architecture	❌	✅	✅	✅	✅	❌	❌	4
Enforcing balance allows local supervised learning in spiking recurrent networks	❌	❌	❌	❌	❌	❌	✅	1
Equilibrated adaptive learning rates for non-convex optimization	✅	❌	✅	❌	❌	❌	✅	3
Estimating Jaccard Index with Missing Observations: A Matrix Calibration Approach	✅	❌	✅	❌	❌	❌	✅	3
Estimating Mixture Models via Mixtures of Polynomials	❌	✅	❌	❌	❌	❌	✅	2
Evaluating the statistical significance of biclusters	✅	❌	❌	❌	❌	❌	❌	1
Exactness of Approximate MAP Inference in Continuous MRFs	❌	❌	❌	❌	❌	❌	❌	0
Expectation Particle Belief Propagation	✅	✅	❌	❌	✅	❌	✅	4
Explore no more: Improved high-probability regret bounds for non-stochastic bandits	✅	❌	❌	❌	❌	❌	✅	2
Exploring Models and Data for Image Question Answering	❌	✅	✅	✅	❌	❌	❌	3
Expressing an Image Stream with a Sequence of Natural Sentences	❌	✅	❌	✅	❌	❌	✅	3
Extending Gossip Algorithms to Distributed Estimation of U-statistics	✅	❌	✅	❌	❌	❌	✅	3
Fast Bidirectional Probability Estimation in Markov Models	✅	❌	✅	❌	❌	❌	✅	3
Fast Classification Rates for High-dimensional Gaussian Generative Models	❌	❌	❌	❌	❌	❌	✅	1
Fast Convergence of Regularized Learning in Games	❌	❌	❌	❌	❌	❌	✅	1
Fast Distributed k-Center Clustering with Outliers on Massive Data	✅	❌	✅	❌	✅	❌	✅	4
Fast Lifted MAP Inference via Partitioning	✅	❌	✅	❌	✅	❌	❌	3
Fast Randomized Kernel Ridge Regression with Statistical Guarantees	✅	❌	✅	✅	❌	❌	✅	4
Fast Rates for Exp-concave Empirical Risk Minimization	❌	❌	❌	❌	❌	❌	❌	0
Fast Second Order Stochastic Backpropagation for Variational Inference	✅	❌	✅	❌	❌	❌	✅	3
Fast Two-Sample Testing with Analytic Representations of Probability Measures	❌	❌	✅	✅	❌	❌	✅	3
Fast and Accurate Inference of Plackett–Luce Models	✅	❌	✅	❌	❌	❌	✅	3
Fast and Guaranteed Tensor Decomposition via Sketching	✅	❌	✅	❌	✅	❌	✅	4
Fast and Memory Optimal Low-Rank Matrix Approximation	✅	❌	❌	❌	❌	❌	❌	1
Fast, Provable Algorithms for Isotonic Regression in all L_p-norms	✅	✅	❌	❌	❌	❌	✅	3
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks	❌	✅	✅	✅	✅	❌	✅	5
Fighting Bandits with a New Kind of Smoothness	✅	❌	❌	❌	❌	❌	❌	1
Finite-Time Analysis of Projected Langevin Monte Carlo	❌	❌	❌	❌	❌	❌	✅	1
Fixed-Length Poisson MRF: Adding Dependencies to the Multinomial	❌	✅	✅	❌	✅	❌	✅	4
Frank-Wolfe Bayesian Quadrature: Probabilistic Integration with Theoretical Guarantees	✅	❌	❌	❌	❌	❌	✅	2
From random walks to distances on unweighted graphs	❌	✅	✅	❌	❌	❌	✅	3
GAP Safe screening rules for sparse multi-task and multi-class models	❌	❌	❌	❌	❌	❌	✅	1
GP Kernels for Cross-Spectrum Analysis	❌	❌	❌	❌	❌	❌	✅	1
Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning	❌	❌	❌	❌	❌	❌	✅	1
Gaussian Process Random Fields	❌	❌	❌	❌	❌	❌	✅	1
Generalization in Adaptive Data Analysis and Holdout Reuse	✅	❌	❌	✅	❌	❌	✅	3
Generative Image Modeling Using Spatial LSTMs	❌	❌	✅	✅	❌	❌	✅	3
Gradient Estimation Using Stochastic Computation Graphs	✅	❌	❌	❌	❌	❌	❌	1
Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families	✅	✅	✅	❌	❌	❌	✅	4
Grammar as a Foreign Language	❌	❌	✅	✅	❌	❌	✅	3
HONOR: Hybrid Optimization for NOn-convex Regularized problems	✅	❌	✅	❌	✅	✅	✅	5
Halting in Random Walk Kernels	❌	✅	✅	✅	✅	✅	✅	6
Hessian-free Optimization for Learning Deep Multidimensional Recurrent Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
Hidden Technical Debt in Machine Learning Systems	❌	❌	❌	❌	❌	❌	❌	0
High Dimensional EM Algorithm: Statistical Optimization and Asymptotic Normality	✅	❌	❌	❌	❌	❌	❌	1
High-dimensional neural spike train analysis with generalized count linear dynamical systems	❌	✅	✅	✅	❌	❌	❌	3
Human Memory Search as Initial-Visit Emitting Random Walk	❌	❌	❌	✅	❌	❌	✅	2
Improved Iteration Complexity Bounds of Cyclic Block Coordinate Descent for Convex Problems	✅	❌	❌	❌	❌	❌	❌	1
Individual Planning in Infinite-Horizon Multiagent Settings: Inference, Structure and Scalability	❌	❌	✅	❌	✅	❌	✅	3
Inference for determinantal point processes without spectral knowledge	❌	❌	✅	✅	❌	❌	✅	3
Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets	❌	✅	✅	✅	❌	❌	✅	4
Infinite Factorial Dynamical Model	✅	✅	✅	❌	❌	❌	✅	4
Information-theoretic lower bounds for convex optimization with erroneous oracles	❌	❌	❌	❌	❌	❌	❌	0
Interactive Control of Diverse Complex Characters with Neural Networks	✅	❌	❌	❌	✅	❌	✅	3
Interpolating Convex and Non-Convex Tensor Decompositions via the Subspace Norm	✅	❌	✅	❌	❌	❌	✅	3
Inverse Reinforcement Learning with Locally Consistent Reward Functions	❌	❌	❌	❌	❌	❌	✅	1
Is Approval Voting Optimal Given Approval Votes?	❌	❌	✅	✅	❌	❌	❌	2
Kullback-Leibler Proximal Variational Inference	✅	❌	✅	✅	❌	❌	✅	4
LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements	❌	❌	❌	❌	❌	❌	✅	1
Large-Scale Bayesian Multi-Label Learning via Topic-Based Label Embeddings	❌	❌	✅	❌	❌	❌	✅	2
Large-scale probabilistic predictors with and without guarantees of validity	✅	❌	✅	✅	❌	❌	✅	4
Latent Bayesian melding for integrating individual and population models	❌	❌	✅	❌	❌	✅	✅	3
Learnability of Influence in Networks	❌	❌	❌	❌	❌	❌	❌	0
Learning Bayesian Networks with Thousands of Variables	✅	✅	✅	❌	❌	❌	✅	4
Learning Causal Graphs with Small Interventions	✅	❌	❌	❌	❌	❌	❌	1
Learning Continuous Control Policies by Stochastic Value Gradients	✅	❌	❌	❌	❌	❌	✅	2
Learning From Small Samples: An Analysis of Simple Decision Heuristics	❌	❌	✅	✅	❌	✅	✅	4
Learning Large-Scale Poisson DAG Models based on OverDispersion Scoring	✅	❌	❌	❌	❌	❌	✅	2
Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels	❌	❌	✅	❌	❌	❌	✅	2
Learning Structured Output Representation using Deep Conditional Generative Models	❌	❌	✅	✅	✅	❌	✅	4
Learning Theory and Algorithms for Forecasting Non-stationary Time Series	❌	❌	✅	❌	❌	❌	❌	1
Learning Wake-Sleep Recurrent Attention Models	❌	❌	✅	✅	❌	❌	❌	2
Learning both Weights and Connections for Efficient Neural Network	❌	❌	✅	✅	✅	❌	✅	4
Learning spatiotemporal trajectories from manifold-valued longitudinal data	✅	❌	✅	❌	❌	❌	✅	3
Learning structured densities via infinite dimensional exponential families	❌	✅	❌	❌	❌	❌	✅	2
Learning to Linearize Under Uncertainty	✅	❌	✅	❌	✅	❌	✅	4
Learning to Segment Object Candidates	❌	❌	✅	✅	✅	❌	✅	4
Learning to Transduce with Unbounded Memory	❌	❌	❌	❌	❌	❌	✅	1
Learning visual biases from human imagination	❌	❌	✅	✅	❌	❌	✅	3
Learning with Group Invariant Features: A Kernel Perspective.	❌	❌	✅	❌	❌	❌	✅	2
Learning with Incremental Iterative Regularization	❌	❌	✅	❌	❌	❌	✅	2
Learning with Relaxed Supervision	✅	✅	❌	❌	❌	❌	✅	3
Learning with Symmetric Label Noise: The Importance of Being Unhinged	❌	❌	✅	❌	❌	❌	✅	2
Learning with a Wasserstein Loss	✅	✅	✅	❌	❌	❌	✅	4
Less is More: Nyström Computational Regularization	✅	✅	✅	✅	✅	❌	✅	6
Lifelong Learning with Non-i.i.d. Tasks	❌	❌	❌	❌	❌	❌	✅	1
Lifted Inference Rules With Constraints	❌	❌	❌	❌	✅	❌	✅	2
Lifted Symmetry Detection and Breaking for MAP Inference	❌	❌	❌	❌	✅	❌	✅	2
Linear Multi-Resource Allocation with Semi-Bandit Feedback	✅	✅	✅	❌	❌	❌	✅	4
Linear Response Methods for Accurate Covariance Estimates from Mean Field Variational Bayes	❌	✅	✅	❌	❌	❌	✅	3
Local Causal Discovery of Direct Causes and Effects	✅	❌	✅	❌	✅	❌	✅	4
Local Expectation Gradients for Black Box Variational Inference	✅	❌	✅	❌	❌	❌	✅	3
Local Smoothness in Variance Reduced Optimization	✅	❌	✅	❌	❌	❌	✅	3
Logarithmic Time Online Multiclass prediction	✅	❌	✅	✅	❌	❌	✅	4
M-Best-Diverse Labelings for Submodular Energies and Beyond	❌	❌	✅	❌	❌	❌	✅	2
M-Statistic for Kernel Change-Point Detection	❌	❌	✅	❌	❌	❌	✅	2
MCMC for Variationally Sparse Gaussian Processes	❌	✅	✅	❌	❌	❌	✅	3
Market Scoring Rules Act As Opinion Pools For Risk-Averse Agents	❌	❌	❌	❌	❌	❌	❌	0
Matrix Completion Under Monotonic Single Index Models	✅	❌	✅	✅	❌	❌	✅	4
Matrix Completion from Fewer Entries: Spectral Detectability and Rank Estimation	✅	✅	❌	❌	❌	❌	✅	3
Matrix Completion with Noisy Side Information	✅	❌	✅	✅	❌	❌	❌	3
Matrix Manifold Optimization for Gaussian Mixtures	✅	✅	✅	❌	❌	❌	✅	4
Max-Margin Deep Generative Models	✅	✅	✅	✅	❌	❌	✅	5
Max-Margin Majority Voting for Learning from Crowds	✅	❌	✅	❌	✅	❌	✅	4
Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets	✅	❌	❌	❌	❌	❌	✅	2
Measuring Sample Quality with Stein's Method	✅	❌	❌	❌	✅	✅	✅	4
Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction	❌	❌	✅	❌	❌	❌	✅	2
Minimax Time Series Prediction	❌	❌	❌	❌	❌	❌	❌	0
Minimum Weight Perfect Matching via Blossom Belief Propagation	✅	❌	❌	❌	❌	❌	❌	1
Mixed Robust/Average Submodular Partitioning: Fast Algorithms, Guarantees, and Applications	✅	❌	✅	❌	❌	❌	✅	3
Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path	✅	❌	❌	❌	❌	❌	❌	1
Model-Based Relative Entropy Stochastic Search	❌	❌	❌	❌	❌	❌	✅	1
Monotone k-Submodular Function Maximization with Size Constraints	✅	❌	✅	❌	✅	❌	✅	4
Multi-Layer Feature Reduction for Tree Structured Group Lasso via Hierarchical Projection	✅	❌	✅	❌	❌	❌	✅	3
Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms	✅	❌	✅	✅	❌	❌	✅	4
NEXT: A System for Real-World Development, Evaluation, and Application of Active Learning	✅	✅	✅	❌	❌	❌	✅	4
Natural Neural Networks	✅	❌	✅	✅	❌	❌	✅	4
Nearly Optimal Private LASSO	✅	❌	❌	❌	❌	❌	❌	1
Neural Adaptive Sequential Monte Carlo	✅	❌	✅	✅	❌	❌	✅	4
Newton-Stein Method: A Second Order Method for GLMs via Stein's Lemma	✅	❌	✅	❌	❌	❌	✅	3
No-Regret Learning in Bayesian Games	❌	❌	❌	❌	❌	❌	❌	0
Non-convex Statistical Optimization for Sparse Tensor Graphical Model	✅	❌	✅	❌	❌	❌	✅	3
Nonparametric von Mises Estimators for Entropies, Divergences and Mutual Informations	❌	✅	✅	✅	❌	❌	✅	4
On Elicitation Complexity	❌	❌	❌	❌	❌	❌	❌	0
On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs	✅	❌	❌	❌	❌	❌	✅	2
On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants	✅	❌	✅	❌	✅	❌	✅	4
On some provably correct cases of variational inference for topic models	✅	❌	❌	❌	❌	❌	❌	1
On the Accuracy of Self-Normalized Log-Linear Models	❌	❌	✅	❌	❌	❌	❌	1
On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators	❌	❌	✅	✅	❌	❌	✅	3
On the Global Linear Convergence of Frank-Wolfe Optimization Variants	✅	❌	✅	❌	❌	❌	❌	2
On the Limitation of Spectral Methods: From the Gaussian Hidden Clique Problem to Rank-One Perturbations of Gaussian Tensors	❌	❌	❌	❌	❌	❌	❌	0
On the Optimality of Classifier Chain for Multi-label Classification	❌	❌	✅	✅	✅	❌	✅	4
On the Pseudo-Dimension of Nearly Optimal Auctions	❌	❌	❌	❌	❌	❌	❌	0
On the consistency theory of high dimensional variable screening	❌	❌	❌	❌	❌	❌	❌	0
On-the-Job Learning with Bayesian Decision Theory	✅	✅	✅	✅	❌	❌	❌	4
Online F-Measure Optimization	✅	❌	✅	✅	❌	❌	✅	4
Online Gradient Boosting	✅	❌	✅	✅	❌	❌	✅	4
Online Learning for Adversaries with Memory: Price of Past Mistakes	✅	❌	❌	❌	❌	❌	❌	1
Online Learning with Adversarial Delays	❌	❌	❌	❌	❌	❌	❌	0
Online Learning with Gaussian Payoffs and Side Observations	✅	❌	❌	❌	❌	❌	❌	1
Online Prediction at the Limit of Zero Temperature	✅	❌	❌	❌	❌	❌	❌	1
Online Rank Elicitation for Plackett-Luce: A Dueling Bandits Approach	✅	❌	❌	❌	❌	❌	✅	2
Optimal Linear Estimation under Unknown Nonlinear Transform	✅	❌	❌	❌	❌	❌	✅	2
Optimal Rates for Random Fourier Features	❌	❌	❌	❌	❌	❌	❌	0
Optimal Ridge Detection using Coverage Risk	❌	❌	✅	✅	❌	❌	✅	3
Optimal Testing for Properties of Distributions	✅	❌	❌	❌	❌	❌	❌	1
Optimization Monte Carlo: Efficient and Embarrassingly Parallel Likelihood-Free Inference	❌	❌	❌	❌	❌	❌	✅	1
Orthogonal NMF through Subspace Exploration	✅	❌	✅	❌	❌	❌	✅	3
Parallel Correlation Clustering on Big Graphs	✅	✅	✅	❌	✅	❌	✅	5
Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation	❌	❌	✅	❌	✅	❌	✅	3
Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions	❌	❌	✅	❌	❌	❌	✅	2
Parallel Recursive Best-First AND/OR Search for Exact MAP Inference in Graphical Models	✅	❌	✅	❌	✅	❌	✅	4
Parallelizing MCMC with Random Partition Trees	✅	✅	✅	❌	❌	❌	✅	4
Particle Gibbs for Infinite Hidden Markov Models	✅	❌	✅	❌	❌	❌	✅	3
Path-SGD: Path-Normalized Optimization in Deep Neural Networks	✅	❌	✅	✅	❌	❌	✅	4
Planar Ultrametrics for Image Segmentation	✅	❌	✅	❌	❌	❌	✅	3
Pointer Networks	❌	❌	❌	❌	❌	❌	✅	1
Policy Evaluation Using the Ω-Return	✅	❌	❌	❌	❌	❌	✅	2
Policy Gradient for Coherent Risk Measures	❌	❌	❌	❌	❌	❌	✅	1
Practical and Optimal LSH for Angular Distance	❌	❌	✅	❌	❌	❌	✅	2
Precision-Recall-Gain Curves: PR Analysis Done Right	❌	✅	✅	✅	❌	❌	❌	3
Preconditioned Spectral Descent for Deep Learning	✅	❌	✅	✅	❌	❌	✅	4
Predtron: A Family of Online Algorithms for General Prediction Problems	✅	❌	❌	❌	❌	❌	❌	1
Principal Differences Analysis: Interpretable Characterization of Differences between Distributions	✅	❌	✅	❌	❌	❌	❌	2
Principal Geodesic Analysis for Probability Measures under the Optimal Transport Metric	✅	❌	✅	❌	✅	❌	❌	3
Private Graphon Estimation for Sparse Graphs	✅	❌	❌	❌	❌	❌	❌	1
Probabilistic Curve Learning: Coulomb Repulsion and the Electrostatic Gaussian Process	❌	❌	❌	❌	❌	❌	✅	1
Probabilistic Line Searches for Stochastic Optimization	❌	❌	✅	❌	❌	❌	✅	2
Probabilistic Variational Bounds for Graphical Models	❌	❌	❌	❌	❌	❌	✅	1
Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling	✅	❌	✅	❌	❌	❌	✅	3
Randomized Block Krylov Methods for Stronger and Faster Approximate Singular Value Decomposition	✅	❌	✅	❌	✅	❌	✅	4
Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width	❌	❌	❌	❌	❌	❌	❌	0
Rate-Agnostic (Causal) Structure Learning	✅	❌	❌	❌	❌	❌	❌	1
Recognizing retinal ganglion cells in the dark	✅	❌	❌	✅	✅	❌	✅	4
Recovering Communities in the General Stochastic Block Model Without Knowing the Parameters	✅	❌	✅	❌	❌	❌	❌	2
Rectified Factor Networks	✅	✅	✅	✅	✅	❌	✅	6
Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Prediction	❌	✅	✅	❌	❌	❌	✅	3
Reflection, Refraction, and Hamiltonian Monte Carlo	✅	❌	❌	❌	❌	❌	✅	2
Regressive Virtual Metric Learning	✅	✅	✅	✅	❌	❌	✅	5
Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring	✅	❌	❌	❌	❌	❌	✅	2
Regret-Based Pruning in Extensive-Form Games	❌	❌	✅	❌	❌	❌	❌	1
Regularization Path of Cross-Validation Error Lower Bounds	✅	✅	✅	✅	✅	❌	✅	6
Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices	❌	❌	✅	❌	❌	❌	✅	2
Regularized EM Algorithms: A Unified Framework and Statistical Guarantees	✅	❌	❌	❌	❌	❌	✅	2
Rethinking LDA: Moment Matching for Discrete ICA	✅	✅	✅	❌	❌	❌	✅	4
Revenue Optimization against Strategic Buyers	❌	❌	❌	❌	❌	❌	❌	0
Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach	✅	✅	❌	❌	❌	❌	✅	3
Robust Feature-Sample Linear Discriminant Analysis for Brain Disorders Diagnosis	✅	❌	✅	✅	❌	❌	✅	4
Robust Gaussian Graphical Modeling with the Trimmed Graphical Lasso	✅	❌	✅	✅	✅	❌	✅	5
Robust PCA with compressed data	❌	❌	✅	✅	❌	❌	✅	3
Robust Portfolio Optimization	❌	❌	✅	❌	❌	❌	✅	2
Robust Regression via Hard Thresholding	✅	❌	❌	❌	✅	❌	✅	3
Robust Spectral Inference for Joint Stochastic Matrix Factorization	❌	❌	✅	❌	❌	❌	✅	2
SGD Algorithms based on Incomplete U-statistics: Large-Scale Minimization of Empirical Risk	❌	❌	✅	❌	❌	❌	✅	2
Saliency, Scale and Information: Towards a Unifying Theory	❌	❌	✅	❌	❌	❌	✅	2
Sample Complexity Bounds for Iterative Stochastic Policy Optimization	✅	❌	❌	❌	❌	❌	✅	2
Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning	✅	❌	❌	❌	❌	❌	❌	1
Sample Complexity of Learning Mahalanobis Distance Metrics	❌	❌	✅	✅	❌	❌	✅	3
Sample Efficient Path Integral Control under Uncertainty	✅	❌	✅	❌	❌	❌	✅	3
Sampling from Probabilistic Submodular Models	✅	❌	✅	❌	❌	❌	✅	3
Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models	❌	✅	✅	❌	❌	❌	❌	2
Scalable Inference for Gaussian Process Models with Black-Box Likelihoods	❌	❌	✅	✅	❌	❌	❌	2
Scalable Semi-Supervised Aggregation of Classifiers	✅	❌	✅	❌	❌	❌	❌	2
Scale Up Nonlinear Component Analysis with Doubly Stochastic Gradients	✅	❌	✅	✅	❌	❌	✅	4
Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks	❌	❌	✅	✅	❌	❌	✅	3
Secure Multi-party Differential Privacy	❌	❌	❌	❌	❌	❌	❌	0
Segregated Graphs and Marginals of Chain Graph Models	❌	❌	❌	❌	❌	❌	✅	1
Semi-Proximal Mirror-Prox for Nonsmooth Composite Minimization	✅	❌	✅	❌	❌	❌	✅	3
Semi-Supervised Factored Logistic Regression for High-Dimensional Neuroimaging Data	❌	✅	✅	❌	❌	❌	✅	3
Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding	❌	✅	✅	✅	❌	❌	✅	4
Semi-supervised Learning with Ladder Networks	✅	✅	✅	✅	❌	❌	✅	5
Semi-supervised Sequence Learning	❌	❌	✅	✅	❌	❌	✅	3
Shepard Convolutional Neural Networks	❌	❌	✅	❌	❌	❌	✅	2
Skip-Thought Vectors	❌	❌	✅	✅	❌	❌	✅	3
Smooth Interactive Submodular Set Cover	✅	❌	❌	❌	❌	❌	✅	2
Smooth and Strong: MAP Inference with Linear Convergence	✅	❌	✅	❌	❌	❌	❌	2
Softstar: Heuristic-Guided Probabilistic Inference	✅	❌	✅	❌	✅	❌	❌	3
Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems	✅	❌	❌	❌	✅	❌	✅	3
Space-Time Local Embeddings	❌	❌	✅	❌	❌	❌	✅	2
Sparse Linear Programming via Primal and Dual Augmented Coordinate Descent	✅	✅	✅	❌	❌	❌	✅	4
Sparse Local Embeddings for Extreme Multi-label Classification	✅	❌	✅	❌	❌	❌	✅	3
Sparse PCA via Bipartite Matchings	✅	❌	✅	❌	❌	❌	✅	3
Sparse and Low-Rank Tensor Decomposition	✅	❌	❌	❌	❌	❌	✅	2
Spatial Transformer Networks	❌	❌	✅	❌	❌	❌	✅	2
Spectral Learning of Large Structured HMMs for Comparative Epigenomics	✅	❌	✅	❌	❌	❌	✅	3
Spectral Norm Regularization of Orthonormal Representations for Graph Transduction	✅	❌	✅	✅	✅	✅	✅	6
Spectral Representations for Convolutional Neural Networks	✅	❌	✅	❌	✅	❌	✅	4
Spherical Random Features for Polynomial Kernels	✅	❌	✅	❌	❌	❌	✅	3
Statistical Model Criticism using Kernel Two Sample Tests	❌	✅	✅	✅	❌	❌	✅	4
Statistical Topological Data Analysis - A Kernel Perspective	❌	✅	✅	❌	❌	❌	✅	3
Stochastic Expectation Propagation	✅	❌	✅	❌	❌	❌	✅	3
Stochastic Online Greedy Learning with Semi-bandit Feedbacks	✅	❌	❌	❌	❌	❌	❌	1
StopWasting My Gradients: Practical SVRG	✅	❌	✅	❌	❌	❌	✅	3
Streaming Min-max Hypergraph Partitioning	✅	❌	✅	❌	❌	❌	✅	3
Streaming, Distributed Variational Inference for Bayesian Nonparametrics	❌	❌	✅	❌	❌	❌	✅	2
Structured Estimation with Atomic Norms: General Bounds and Applications	✅	❌	❌	❌	❌	❌	❌	1
Structured Transforms for Small-Footprint Deep Learning	✅	❌	✅	✅	✅	❌	✅	5
SubmodBoxes: Near-Optimal Search for a Set of Diverse Object Proposals	❌	❌	✅	✅	❌	❌	✅	3
Submodular Hamming Metrics	✅	❌	✅	❌	❌	❌	✅	3
Subsampled Power Iteration: a Unified Algorithm for Block Models and Planted CSP's	✅	❌	❌	❌	❌	❌	❌	1
Subset Selection by Pareto Optimization	✅	❌	✅	✅	❌	❌	✅	4
Subspace Clustering with Irrelevant Features via Robust Dantzig Selector	❌	❌	❌	❌	❌	❌	✅	1
Sum-of-Squares Lower Bounds for Sparse PCA	✅	❌	❌	❌	❌	❌	❌	1
Super-Resolution Off the Grid	✅	❌	❌	❌	❌	❌	❌	1
Supervised Learning for Dynamical System Learning	❌	❌	✅	✅	❌	❌	✅	3
Synaptic Sampling: A Bayesian Approach to Neural Network Plasticity and Rewiring	❌	❌	✅	❌	❌	❌	✅	2
Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms	❌	❌	✅	❌	✅	❌	✅	3
Teaching Machines to Read and Comprehend	❌	✅	✅	✅	❌	❌	✅	4
Tensorizing Neural Networks	❌	✅	✅	✅	✅	❌	✅	5
Testing Closeness With Unequal Sized Samples	✅	❌	✅	❌	❌	❌	✅	3
Texture Synthesis Using Convolutional Neural Networks	❌	✅	✅	✅	❌	❌	✅	4
The Brain Uses Reliability of Stimulus Information when Making Perceptual Decisions	❌	❌	✅	❌	❌	❌	✅	2
The Consistency of Common Neighbors for Link Prediction in Stochastic Blockmodels	✅	❌	❌	✅	❌	❌	✅	3
The Human Kernel	❌	❌	✅	❌	❌	❌	✅	2
The Pareto Regret Frontier for Bandits	✅	✅	❌	❌	❌	❌	✅	3
The Poisson Gamma Belief Network	✅	✅	✅	✅	✅	❌	✅	6
The Population Posterior and Bayesian Modeling on Streams	✅	❌	✅	✅	❌	❌	✅	4
The Return of the Gating Network: Combining Generative Models and Discriminative Training in Natural Image Priors	❌	✅	✅	❌	❌	✅	✅	4
The Self-Normalized Estimator for Counterfactual Learning	❌	✅	✅	✅	❌	❌	✅	4
Time-Sensitive Recommendation From Recurrent User Activities	✅	❌	✅	✅	❌	❌	✅	4
Top-k Multiclass SVM	✅	✅	✅	✅	❌	❌	❌	4
Tractable Bayesian Network Structure Learning with Bounded Vertex Cover Number	❌	✅	✅	❌	❌	✅	✅	4
Tractable Learning for Complex Probability Queries	✅	❌	✅	✅	✅	❌	✅	5
Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy	❌	✅	✅	✅	✅	❌	✅	5
Training Very Deep Networks	❌	✅	✅	✅	❌	❌	✅	4
Tree-Guided MCMC Inference for Normalized Random Measure Mixture Models	❌	❌	✅	❌	❌	❌	✅	2
Unified View of Matrix Completion under General Structural Constraints	❌	❌	❌	❌	❌	❌	❌	0
Unlocking neural population non-stationarities using hierarchical dynamics models	❌	✅	✅	✅	❌	❌	✅	4
Unsupervised Learning by Program Synthesis	✅	❌	✅	❌	❌	❌	✅	3
Variance Reduced Stochastic Gradient Descent with Neighbors	❌	❌	✅	❌	❌	❌	✅	2
Variational Consensus Monte Carlo	❌	❌	✅	❌	❌	❌	✅	2
Variational Dropout and the Local Reparameterization Trick	❌	❌	✅	✅	❌	❌	✅	3
Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning	✅	❌	❌	❌	❌	❌	✅	2
Visalogy: Answering Visual Analogy Questions	❌	❌	✅	✅	❌	❌	✅	3
Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis	❌	❌	✅	❌	✅	❌	✅	3
Weighted Theta Functions and Embeddings with Applications to Max-Cut, Clustering and Summarization	✅	❌	✅	❌	❌	❌	✅	3
When are Kalman-Filter Restless Bandits Indexable?	❌	❌	❌	❌	❌	❌	❌	0
Where are they looking?	❌	✅	✅	✅	❌	❌	✅	4
Winner-Take-All Autoencoders	❌	✅	✅	❌	❌	❌	✅	3
b-bit Marginal Regression	❌	❌	❌	❌	❌	❌	✅	1