JMLR · Scour

Categorical Semantics of Compositional Reinforcement Learning

On the O(sqrt(d)/T^(1/4)) Convergence Rate of RMSProp and Its Momentum Extension Measured by l_1 Norm

Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability

PREMAP: A Unifying PREiMage APproximation Framework for Neural Networks

Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning

Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary

Diffeomorphism-based feature learning using Poincaré inequalities on augmented input space

Randomly Projected Convex Clustering Model: Motivation, Realization, and Cluster Recovery Guarantees

Optimal and Efficient Algorithms for Decentralized Online Convex Optimization

Finite Expression Method for Solving High-Dimensional Partial Differential Equations

Deep Variational Multivariate Information Bottleneck - A Framework for Variational Losses

ClimSim-Online: A Large Multi-Scale Dataset and Framework for Hybrid Physics-ML Climate Emulation

Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching

Fine-grained Analysis and Faster Algorithms for Iteratively Solving Linear Systems

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory

Deep Generative Models: Complexity, Dimensionality, and Approximation

Dynamic Bayesian Learning for Spatiotemporal Mechanistic Models

Latent Process Models for Functional Network Data

Losing Momentum in Continuous-time Stochastic Optimisation

Randomization Can Reduce Both Bias and Variance: A Case Study in Random Forests

Log in to enable infinite scrolling