NeurIPS 2019 accepted papers on Learning theory and algorithms
279 of the 1,429 papers accepted at NeurIPS 2019 (19.5%) are on Learning theory and algorithms, compared with 20.4% at NeurIPS 2018. They fall into 9 topics.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Prediction and decision losses · 68 papers
- Explanations can be manipulated and geometry is to blame (144 citations)
- Verified Uncertainty Calibration (138 citations)
- On the Accuracy of Influence Functions for Measuring Group Effects (82 citations)
- A Debiased MDI Feature Importance Measure for Random Forests (80 citations)
- Bayesian Batch Active Learning as Sparse Subset Approximation (66 citations)
- Controlling Neural Level Sets (62 citations)
- Statistical Analysis of Nearest Neighbor Methods for Anomaly Detection (60 citations)
- A Step Toward Quantifying Independently Reproducible Machine Learning Research (58 citations)
- Conformalized Quantile Regression (49 citations)
- Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks (46 citations)
- Large Scale Structure of Neural Network Loss Landscapes (44 citations)
- Robust Attribution Regularization (38 citations)
and 56 more in the interactive map.
Matrix and tensor methods · 52 papers
- Block Coordinate Regularization by Denoising (49 citations)
- Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery (37 citations)
- Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing (34 citations)
- The Impact of Regularization on High-dimensional Logistic Regression (27 citations)
- Variance Reduction for Matrix Games (25 citations)
- Asymptotics for Sketching in Least Squares Regression (24 citations)
- On Robustness of Principal Component Regression (22 citations)
- Missing Not at Random in Matrix Completion: The Effectiveness of Estimating Missingness Probabilities Under a Low Nuclear Norm Assumption (19 citations)
- Optimal Sketching for Kronecker Product Regression and Low Rank Approximation (19 citations)
- Learning-Based Low-Rank Approximations (18 citations)
- The spiked matrix model with generative priors (18 citations)
- Handling correlated and repeated measurements with the smoothed multivariate square-root Lasso (17 citations)
and 40 more in the interactive map.
Sample complexity · 50 papers
- Certainty Equivalence is Efficient for Linear Quadratic Control (88 citations)
- Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning (60 citations)
- Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection (55 citations)
- Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation (54 citations)
- Distribution-Independent PAC Learning of Halfspaces with Massart Noise (35 citations)
- Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory (34 citations)
- Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models (30 citations)
- Concentration of risk measures: A Wasserstein distance approach (26 citations)
- On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective (26 citations)
- PAC-Bayes under potentially heavy tails (19 citations)
- Wasserstein Dependency Measure for Representation Learning (19 citations)
- Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models (17 citations)
and 38 more in the interactive map.
Kernels and regression theory · 27 papers
- What Can ResNet Learn Efficiently, Going Beyond Kernels? (94 citations)
- Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control (52 citations)
- Random deep neural networks are biased towards simple functions (30 citations)
- On the number of variables to use in principal component regression (22 citations)
- Distributionally Robust Optimization and Generalization in Kernel Methods (15 citations)
- On the Downstream Performance of Compressed Word Embeddings (15 citations)
- Fast, Provably convergent IRLS Algorithm for p-norm Linear Regression (14 citations)
- Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes (13 citations)
- Generalization in multitask deep neural classifiers: a statistical physics approach (12 citations)
- Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis (11 citations)
- Hypothesis Set Stability and Generalization (11 citations)
- Margin-Based Generalization Lower Bounds for Boosted Classifiers (11 citations)
and 15 more in the interactive map.
Submodular and game algorithms · 18 papers
- Efficient and Thrifty Voting by Any Means Necessary (26 citations)
- Multiagent Evaluation under Incomplete Information (21 citations)
- Learning to Correlate in Multi-Player General-Sum Sequential Games (19 citations)
- Adaptive Influence Maximization with Myopic Feedback (18 citations)
- Envy-Free Classification (15 citations)
- Interlaced Greedy Algorithm for Maximization of Submodular Functions in Nearly Linear Time (13 citations)
- Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions (13 citations)
- Discrimination in Online Markets: Effects of Social Bias on Learning from Reviews and Policy Design (12 citations)
- Optimizing Generalized Rate Metrics with Three Players (12 citations)
- Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks (10 citations)
- Manipulating a Learning Defender and Ways to Counteract (10 citations)
- Optimal Pricing in Repeated Posted-Price Auctions with Different Patience of the Seller and the Buyer (10 citations)
and 6 more in the interactive map.
Combinatorial and search optimization · 18 papers
- Neural Lyapunov Control (130 citations)
- Write, Execute, Assess: Program Synthesis with a REPL (59 citations)
- Learning Local Search Heuristics for Boolean Satisfiability (51 citations)
- Pareto Multi-Task Learning (47 citations)
- Robustness Verification of Tree-based Models (38 citations)
- Depth-First Proof-Number Search with Heuristic Edge Cost and Application to Chemical Synthesis Planning (28 citations)
- A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning (26 citations)
- Compiler Auto-Vectorization with Imitation Learning (23 citations)
- SPoC: Search-based Pseudocode to Code (10 citations)
- GENO -- GENeric Optimization for Classical Machine Learning (9 citations)
- Multi-objective Bayesian optimisation with preferences over objectives (9 citations)
- Cost Effective Active Search (8 citations)
and 6 more in the interactive map.
Clustering · 18 papers
- q-means: A quantum algorithm for unsupervised machine learning (108 citations)
- Making AI Forget You: Data Deletion in Machine Learning (69 citations)
- Fair Algorithms for Clustering (59 citations)
- Coresets for Clustering with Fairness Constraints (57 citations)
- Selective Sampling-based Scalable Sparse Subspace Clustering (38 citations)
- Multiway clustering via tensor block models (28 citations)
- Subquadratic High-Dimensional Hierarchical Clustering (18 citations)
- Revisiting the Bethe-Hessian: Improved Community Detection in Sparse Heterogeneous Graphs (14 citations)
- Greedy Sampling for Approximate Clustering in the Presence of Outliers (12 citations)
- Fully Dynamic Consistent Facility Location (11 citations)
- Foundations of Comparison-Based Hierarchical Clustering (10 citations)
- k-Means Clustering of Lines for Big Data (10 citations)
and 6 more in the interactive map.
Optimal transport · 16 papers
- Hierarchical Optimal Transport for Document Representation (49 citations)
- Differentiable Ranking and Sorting using Optimal Transport (48 citations)
- Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem (41 citations)
- Hierarchical Optimal Transport for Multimodal Distribution Alignment (30 citations)
- Sliced Gromov-Wasserstein (23 citations)
- Screening Sinkhorn Algorithm for Regularized Optimal Transport (21 citations)
- Discriminator optimal transport (17 citations)
- Massively scalable Sinkhorn distances via the Nyström method (16 citations)
- A Graph Theoretic Additive Approximation of Optimal Transport (12 citations)
- Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections (10 citations)
- Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance (8 citations)
- Interior-Point Methods Strike Back: Solving the Wasserstein Barycenter Problem (6 citations)
and 4 more in the interactive map.
Fairness · 12 papers
- Policy Learning for Fairness in Ranking (97 citations)
- Unlocking Fairness: a Trade-off Revisited (54 citations)
- Balancing Efficiency and Fairness in On-Demand Ridesourcing (45 citations)
- PC-Fairness: A Unified Framework for Measuring Causality-based Fairness (44 citations)
- The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the XAUC Metric (40 citations)
- Noise-tolerant fair classification (31 citations)
- Average Individual Fairness: Algorithms, Generalization and Experiments (28 citations)
- Inherent Tradeoffs in Learning Fair Representations (28 citations)
- Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification (25 citations)
- Paradoxes in Fair Machine Learning (15 citations)
- Multi-Criteria Dimensionality Reduction with Applications to Fairness (14 citations)
- Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairness (13 citations)
