JMLR 2026 papers on Learning theory and algorithms
45 of the 196 papers published in JMLR 2026 (23.0%) are on Learning theory and algorithms, compared with 27.5% at JMLR 2025. They fall into 8 topics.
See JMLR 2026 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
Prediction and decision losses · 11 papers
- Contrasting Local and Global Modeling with Machine Learning and Satellite Data: A Case Study Estimating Tree Canopy Height in African Savannas (8 citations)
- Feedback-Enhanced Online Multiple Testing with Applications to Conformal Selection (5 citations)
- Deep Neural Expected Shortfall Regression with Tail-Robustness (2 citations)
- Approximation-Free Differentiable Oblique Decision Trees
- Inference with non-differentiable surrogate loss in a general high-dimensional classification framework
- Doubly Debiased Robust Subsampling for Transfer Learning
- Kernel-based Distributed Learning Beyond Least Squares
- Model-free generalized fiducial inference
- Pairwise Comparisons without Stochastic Transitivity: Model, Theory and Applications
- Three Types of Calibration using Properties and their Semantic and Formal Relationships
- Transfer Conformal Predictive Inference for Regression
Sample complexity · 10 papers
- From learnable objects to learnable random objects (4 citations)
- Mixing times of data-augmentation Gibbs samplers for high-dimensional probit regression (4 citations)
- Nonlocal Techniques for the Analysis of Deep ReLU Neural Network Approximations (4 citations)
- Conditional Regression for the Nonlinear Single-Variable Model (2 citations)
- Error Analysis for Deep ReLU Feedforward Density-Ratio Estimation with Bregman Divergence
- Generalized Resubstitution for Regression Error Estimation
- High-dimensional Parameter Transfer With Fused-Regularizer
- A Data-Augmented Contrastive Learning Approach to Nonparametric Density Estimation
- Persistence Diagrams Estimation of Multivariate Piecewise Hölder-continuous Signals
- Statistical Inference for High-dimensional Partially Linear Models via Debiased Rank Lasso
Kernels and regression theory · 10 papers
- Statistical Learning Theory for Neural Operators (18 citations)
- Have ASkotch: A Neat Solution for Large-Scale Kernel Ridge Regression (14 citations)
- Nested Subspace Learning with Flags (4 citations)
- Exogenous Randomness Empowering Random Forests (3 citations)
- Spectral Truncation Kernels: Noncommutativity in C*-algebraic Kernel Machines (2 citations)
- Pointwise Confidence Estimation in the Non-linear $\ell^2$-regularized Least Squares
- Transfer Learning via Regularized Random-effects Linear Discriminant Analysis
- Nonlinear function-on-function regression by RKHS
- Optimal Approximation and Generalization Errors for Deep Convolutional Neural Networks
- The Distribution of Ridgeless Least Squares Interpolators
Matrix and tensor methods · 5 papers
- Canonical Correlation Analysis as Reduced Rank Regression in High Dimensions (3 citations)
- Efficient frequent directions algorithms for approximate decomposition of matrices and higher-order tensors
- Online Generalized Sparse Regression: How Does Overparametrization Help?
- Adaptive Forward Stepwise: A Method for High Sparsity Regression
- Sparse Topic Modeling via Spectral Decomposition and Thresholding
Optimal transport · 4 papers
- Global Fréchet Manifold Learning for Random Objects, With Application to Low-Dimensional Wasserstein Representations of Distributional Data
- Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications
- skwdro: a library for Wasserstein distributionally robust machine learning
- Sliced Wasserstein Regression
