JMLR 2023 papers on Learning theory and algorithms
114 of the 354 papers published in JMLR 2023 (32.2%) are on Learning theory and algorithms, compared with 38.2% at JMLR 2022. They fall into 9 topics.
See JMLR 2023 in the interactive map
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
Kernels and regression theory · 28 papers
- Interpolating Classifiers Make Few Mistakes (27 citations)
- Two Sample Testing in High Dimension via Maximum Mean Discrepancy (15 citations)
- The Implicit Bias of Benign Overfitting (11 citations)
- Ridges, Neural Networks, and the Radon Transform (9 citations)
- Bagging in overparameterized learning: Risk characterization and risk monotonization (8 citations)
- Reproducing Kernels and New Approaches in Compositional Data Analysis (8 citations)
- A Permutation-Free Kernel Independence Test (5 citations)
- Distributed Nonparametric Regression Imputation for Missing Response Problems with Large-scale Data (2 citations)
- Modular Regression: Improving Linear Models by Incorporating Auxiliary Data (2 citations)
- Dimensionality Reduction and Wasserstein Stability for Kernel Regression (1 citation)
- Generalization error bounds for multiclass sparse linear classifiers (1 citation)
- Graph-Aided Online Multi-Kernel Learning (1 citation)
and 16 more in the interactive map.
Matrix and tensor methods · 26 papers
- Low-rank Tensor Estimation via Riemannian Gauss-Newton: Statistical Optimality and Second-Order Convergence (16 citations)
- Sensing Theorems for Unsupervised Learning in Linear Inverse Problems (14 citations)
- Implicit Regularization and Entrywise Convergence of Riemannian Optimization for Low Tucker-Rank Tensor Completion (13 citations)
- Non-Asymptotic Guarantees for Robust Statistical Learning under Infinite Variance Assumption (12 citations)
- Sparse Plus Low Rank Matrix Decomposition: A Discrete Optimization Approach (10 citations)
- L0Learn: A Scalable Package for Sparse Learning using L0 Regularization (9 citations)
- Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices (9 citations)
- Outlier-Robust Subsampling Techniques for Persistent Homology (9 citations)
- Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification (8 citations)
- Statistical Inference for Noisy Incomplete Binary Matrix (8 citations)
- Dynamic Ranking with the BTL Model: A Nearest Neighbor based Rank Centrality Method (5 citations)
- Sparse PCA: a Geometric Approach (5 citations)
and 14 more in the interactive map.
Prediction and decision losses · 22 papers
- On Tilted Losses in Machine Learning: Theory and Applications (26 citations)
- Random Forests for Change Point Detection (24 citations)
- Calibrated Multiple-Output Quantile Regression with Representation Learning (22 citations)
- On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results (21 citations)
- Optimal Strategies for Reject Option Classifiers (20 citations)
- Selection by Prediction with Conformal p-values (19 citations)
- Attribution-based Explanations that Provide Recourse Cannot be Robust (17 citations)
- Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees (12 citations)
- T-Cal: An Optimal Test for the Calibration of Predictive Models (11 citations)
- Deletion and Insertion Tests in Regression Models (9 citations)
- Efficient Computation of Rankings from Pairwise Comparisons (9 citations)
- Minimax Risk Classifiers with 0-1 Loss (4 citations)
and 10 more in the interactive map.
Clustering · 13 papers
- Selective inference for k-means clustering (46 citations)
- The Hyperspherical Geometry of Community Detection: Modularity as a Distance (6 citations)
- Large data limit of the MBO scheme for data clustering: convergence of the dynamics (4 citations)
- A Group-Theoretic Approach to Computational Abstraction: Symmetry-Driven Hierarchical Clustering
- Adaptive Clustering Using Kernel Density Estimators
- Augmented Sparsifiers for Generalized Hypergraph Cuts
- Autoregressive Networks
- Clustering with Tangles: Algorithmic Framework and Theoretical Guarantees
- Community models for networks observed through edge nominations
- Consistent Model-based Clustering using the Quasi-Bernoulli Stick-breaking Process
- Escaping The Curse of Dimensionality in Bayesian Model-Based Clustering
- Higher-Order Spectral Clustering Under Superimposed Stochastic Block Models
and 1 more in the interactive map.
Sample complexity · 10 papers
- Operator learning with PCA-Net: upper and lower complexity bounds (19 citations)
- From Understanding Genetic Drift to a Smart-Restart Mechanism for Estimation-of-Distribution Algorithms (4 citations)
- Limitations on approximation by deep and shallow neural networks (3 citations)
- Adaptive Learning of Density Ratios in RKHS
- Tractable and Near-Optimal Adversarial Algorithms for Robust Estimation in Contaminated Gaussian Models
- Distributed Statistical Inference under Heterogeneity
- Dropout Training is Distributionally Robust Optimal
- Least Squares Model Averaging for Distributed Data
- On Batch Teaching Without Collusion
- Sample Complexity for Distributionally Robust Learning under chi-square divergence
Optimal transport · 4 papers
- On Unbalanced Optimal Transport: Gradient Methods, Sparsity and Approximation Error (10 citations)
- Importance Sparsification for Sinkhorn Algorithm (8 citations)
- Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning (4 citations)
- Multivariate Soft Rank via Entropy-Regularized Optimal Transport: Sample Efficiency and Generative Modeling
