JMLR 2025 papers on Learning theory and algorithms
82 of the 298 papers published in JMLR 2025 (27.5%) are on Learning theory and algorithms, compared with 33.8% at JMLR 2024. They fall into 9 topics.
See JMLR 2025 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 · 20 papers
- Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness (34 citations)
- Randomization Can Reduce Both Bias and Variance: A Case Study in Random Forests (14 citations)
- Universality of Kernel Random Matrices and Kernel Regression in the Quadratic Regime (12 citations)
- Bayes Meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes (11 citations)
- Nonlinear functional regression by functional deep neural network with kernel embedding (10 citations)
- Data-Driven Performance Guarantees for Classical and Learned Optimizers (9 citations)
- Integral Probability Metrics Meet Neural Networks: The Radon-Kolmogorov-Smirnov Test (9 citations)
- Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions (8 citations)
- Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling (5 citations)
- Learning conditional distributions on continuous spaces (4 citations)
- On the Approximation of Kernel functions (2 citations)
- Diffeomorphism-based feature learning using Poincaré inequalities on augmented input space (1 citation)
and 8 more in the interactive map.
Matrix and tensor methods · 15 papers
- Fine-grained Analysis and Faster Algorithms for Iteratively Solving Linear Systems (10 citations)
- A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation (4 citations)
- High-Rank Irreducible Cartesian Tensor Decomposition and Bases of Equivariant Spaces (3 citations)
- Selective Inference with Distributed Data (2 citations)
- Sparse SVM with Hard-Margin Loss: a Newton-Augmented Lagrangian Method in Reduced Dimensions (2 citations)
- Geometry-Dependent Matching Pursuit: a Transition Phase for Convergence on Linear Regression and LASSO (1 citation)
- Sparse Semiparametric Discriminant Analysis for High-dimensional Zero-inflated Data (1 citation)
- Dynamic angular synchronization under smoothness constraints
- Affine Rank Minimization via Asymptotic Log-Det Iteratively Reweighted Least Squares
- High-Dimensional L2-Boosting: Rate of Convergence
- Inferring Change Points in High-Dimensional Regression via Approximate Message Passing
- Manifold Fitting under Unbounded Noise
and 3 more in the interactive map.
Prediction and decision losses · 15 papers
- A Unified Framework to Enforce, Discover, and Promote Symmetry in Machine Learning (28 citations)
- CAP: A General Algorithm for Online Selective Conformal Prediction with FCR Control (12 citations)
- TorchCP: A Python Library for Conformal Prediction (10 citations)
- Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning (9 citations)
- Bias-variance decompositions: the exclusive privilege of Bregman divergences (8 citations)
- Four Axiomatic Characterizations of the Integrated Gradients Attribution Method (7 citations)
- On Probabilistic Embeddings in Optimal Dimension Reduction (4 citations)
- Model-free Change-Point Detection Using AUC of a Classifier (3 citations)
- Are Ensembles Getting Better All the Time? (1 citation)
- depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers (1 citation)
- Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks
- A Comparative Evaluation of Quantification Methods
and 3 more in the interactive map.
Sample complexity · 13 papers
- On the Robustness of Kernel Goodness-of-Fit Tests (12 citations)
- From Sparse to Dense Functional Data in High Dimensions: Revisiting Phase Transitions from a Non-Asymptotic Perspective (5 citations)
- Generalized multi-view model: Adaptive density estimation under low-rank constraints (4 citations)
- Distribution Estimation under the Infinity Norm (3 citations)
- Frontiers to the learning of nonparametric hidden Markov models (3 citations)
- Deep Neural Networks are Adaptive to Function Regularity and Data Distribution in Approximation and Estimation (2 citations)
- Error estimation and adaptive tuning for unregularized robust M-estimator (2 citations)
- Density Estimation Using the Perceptron (1 citation)
- How good is your Laplace approximation of the Bayesian posterior? Finite-sample computable error bounds for a variety of useful divergences
- Instability, Computational Efficiency and Statistical Accuracy
- Linear Hypothesis Testing in High-Dimensional Expected Shortfall Regression with Heavy-Tailed Errors
- Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary
and 1 more in the interactive map.
Optimal transport · 7 papers
- Geometric Operator Learning with Optimal Transport (20 citations)
- The Z-Gromov-Wasserstein Distance (13 citations)
- Sliced-Wasserstein Distances and Flows on Cartan-Hadamard Manifolds (9 citations)
- Geometry and Stability of Supervised Learning Problems (1 citation)
- Robust Point Matching with Distance Profiles
- Unbalanced Kantorovich-Rubinstein distance, plan, and barycenter on nite spaces: A statistical perspective
- Wasserstein F-tests for Frechet regression on Bures-Wasserstein manifolds
Clustering · 4 papers
- Randomly Projected Convex Clustering Model: Motivation, Realization, and Cluster Recovery Guarantees (3 citations)
- An Axiomatic Definition of Hierarchical Clustering
- Step and Smooth Decompositions as Topological Clustering
- Bagged k-Distance for Mode-Based Clustering Using the Probability of Localized Level Sets
Combinatorial and search optimization · 4 papers
- PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks (6 citations)
- Reliever: Relieving the Burden of Costly Model Fits for Changepoint Detection (4 citations)
- Fast Computation of Superquantile-Constrained Optimization Through Implicit Scenario Reduction (3 citations)
- skglm: Improving scikit-learn for Regularized Generalized Linear Models
