NeurIPS 2018 accepted papers on Learning theory and algorithms
206 of the 1,008 papers accepted at NeurIPS 2018 (20.4%) are on Learning theory and algorithms, compared with 27.3% at NeurIPS 2017. They fall into 9 topics.
See NeurIPS 2018 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 · 46 papers
- CatBoost: unbiased boosting with categorical features (1,125 citations)
- To Trust Or Not To Trust A Classifier (278 citations)
- Algorithms and Theory for Multiple-Source Adaptation (122 citations)
- On the Dimensionality of Word Embedding (112 citations)
- Are GANs Created Equal? A Large-Scale Study (77 citations)
- Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity (77 citations)
- Dendritic cortical microcircuits approximate the backpropagation algorithm (68 citations)
- A Model for Learned Bloom Filters and Optimizing by Sandwiching (58 citations)
- Alternating optimization of decision trees, with application to learning sparse oblique trees (50 citations)
- Adding One Neuron Can Eliminate All Bad Local Minima (44 citations)
- Human-in-the-Loop Interpretability Prior (44 citations)
- When do random forests fail? (42 citations)
and 34 more in the interactive map.
Matrix and tensor methods · 41 papers
- Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds (151 citations)
- Low-Rank Tucker Decomposition of Large Tensors Using TensorSketch (69 citations)
- Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation (61 citations)
- Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis (46 citations)
- Leveraged volume sampling for linear regression (43 citations)
- Computing Higher Order Derivatives of Matrix and Tensor Expressions (29 citations)
- Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms (21 citations)
- Boosted Sparse and Low-Rank Tensor Regression (20 citations)
- A Dual Framework for Low-rank Tensor Completion (19 citations)
- Spectral Filtering for General Linear Dynamical Systems (17 citations)
- Phase Retrieval Under a Generative Prior (16 citations)
- Legendre Decomposition for Tensors (14 citations)
and 29 more in the interactive map.
Sample complexity · 38 papers
- Lipschitz regularity of deep neural networks: analysis and efficient estimation (135 citations)
- Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model (85 citations)
- The Price of Fair PCA: One Extra dimension (77 citations)
- Adversarially Robust Optimization with Gaussian Processes (46 citations)
- A Convex Duality Framework for GANs (38 citations)
- Robust Hypothesis Testing Using Wasserstein Uncertainty Sets (34 citations)
- The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-Optimal (33 citations)
- Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes (32 citations)
- Nonparametric Density Estimation under Adversarial Losses (31 citations)
- Robust Learning of Fixed-Structure Bayesian Networks (23 citations)
- On Coresets for Logistic Regression (20 citations)
- Q-learning with Nearest Neighbors (17 citations)
and 26 more in the interactive map.
Kernels and regression theory · 20 papers
- Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate (140 citations)
- Entropy and mutual information in models of deep neural networks (139 citations)
- Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features (91 citations)
- Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagrams (49 citations)
- Learning To Learn Around A Common Mean (39 citations)
- Multi-Class Learning: From Theory to Algorithm (34 citations)
- Generalization Bounds for Uniformly Stable Algorithms (31 citations)
- But How Does It Work in Theory? Linear SVM with Random Features (30 citations)
- Quadrature-based features for kernel approximation (30 citations)
- The committee machine: Computational to statistical gaps in learning a two-layers neural network (28 citations)
- Hunting for Discriminatory Proxies in Linear Regression Models (15 citations)
- On Fast Leverage Score Sampling and Optimal Learning (15 citations)
and 8 more in the interactive map.
Combinatorial and search optimization · 16 papers
- Multi-Task Learning as Multi-Objective Optimization (327 citations)
- A Unified View of Piecewise Linear Neural Network Verification (133 citations)
- Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN (123 citations)
- Learning Loop Invariants for Program Verification (54 citations)
- Boolean Decision Rules via Column Generation (53 citations)
- Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections (36 citations)
- Monte-Carlo Tree Search for Constrained POMDPs (30 citations)
- Proximal Graphical Event Models (25 citations)
- Single-Agent Policy Tree Search With Guarantees (18 citations)
- Fast Similarity Search via Optimal Sparse Lifting (15 citations)
- Neural Guided Constraint Logic Programming for Program Synthesis (15 citations)
- Topkapi: Parallel and Fast Sketches for Finding Top-K Frequent Elements (10 citations)
and 4 more in the interactive map.
Submodular and game algorithms · 15 papers
- Do Less, Get More: Streaming Submodular Maximization with Subsampling (42 citations)
- On Misinformation Containment in Online Social Networks (31 citations)
- Ex ante coordination and collusion in zero-sum multi-player extensive-form games (23 citations)
- Optimal Algorithms for Continuous Non-monotone Submodular and DR-Submodular Maximization (23 citations)
- A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers (21 citations)
- Non-monotone Submodular Maximization in Exponentially Fewer Iterations (17 citations)
- Learning from Group Comparisons: Exploiting Higher Order Interactions (16 citations)
- Solving Large Sequential Games with the Excessive Gap Technique (14 citations)
- Optimization for Approximate Submodularity (8 citations)
- Practical exact algorithm for trembling-hand equilibrium refinements in games (7 citations)
- Universal Growth in Production Economies (5 citations)
- A Unified Framework for Extensive-Form Game Abstraction with Bounds (4 citations)
and 3 more in the interactive map.
Clustering · 13 papers
- Understanding Regularized Spectral Clustering via Graph Conductance (50 citations)
- Overlapping Clustering Models, and One (class) SVM to Bind Them All (24 citations)
- Distributed $k$-Clustering for Data with Heavy Noise (13 citations)
- A Practical Algorithm for Distributed Clustering and Outlier Detection (12 citations)
- Bipartite Stochastic Block Models with Tiny Clusters (12 citations)
- Data-Driven Clustering via Parameterized Lloyd's Families (12 citations)
- The Cluster Description Problem - Complexity Results, Formulations and Approximations (11 citations)
- How to tell when a clustering is (approximately) correct using convex relaxations (6 citations)
- Scalable Laplacian K-modes (6 citations)
- Approximation algorithms for stochastic clustering (4 citations)
- Query K-means Clustering and the Double Dixie Cup Problem (2 citations)
- Clustering Redemption–Beyond the Impossibility of Kleinberg’s Axioms
and 1 more in the interactive map.
Optimal transport · 9 papers
- Neural Architecture Search with Bayesian Optimisation and Optimal Transport (262 citations)
- Minimax Statistical Learning with Wasserstein distances (72 citations)
- Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance (70 citations)
- On the Convergence and Robustness of Training GANs with Regularized Optimal Transport (58 citations)
- Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions (45 citations)
- Distilled Wasserstein Learning for Word Embedding and Topic Modeling (31 citations)
- Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport (31 citations)
- Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds (6 citations)
- Computing Kantorovich-Wasserstein Distances on $d$-dimensional histograms using $(d+1)$-partite graphs (5 citations)
Fairness · 8 papers
- Why Is My Classifier Discriminatory? (153 citations)
- Fairness Through Computationally-Bounded Awareness (93 citations)
- Empirical Risk Minimization Under Fairness Constraints (85 citations)
- Does mitigating ML's impact disparity require treatment disparity? (78 citations)
- Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer (56 citations)
- Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making (46 citations)
- Enhancing the Accuracy and Fairness of Human Decision Making (20 citations)
- On preserving non-discrimination when combining expert advice (17 citations)
