Learning a Sparse Representation of Barron Functions with the Inverse Scale Space Flow

by Tjeerd Jan Heeringa, Tim Roith, Christoph Brune & Martin Burger, JML 4 (2025), pp. 48-88.

A Note on Continuous-Time Online Learning

by Lexing Ying, JML 4 (2025), pp. 1-10.

Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces

by Andrea Angiuli, Jean-Pierre Fouque, Ruimeng Hu & Alan Raydan, JML 4 (2025), pp. 11-47.

Solving Bivariate Kinetic Equations for Polymer Diffusion Using Deep Learning

by Heng Wang & Weihua Deng, JML 3 (2024), pp. 215-244.

On the Existence of Optimal Shallow Feedforward Networks with ReLU Activation

by Steffen Dereich & Sebastian Kassing, JML 3 (2024), pp. 1-22.

Stochastic Delay Differential Games: Financial Modeling and Machine Learning Algorithms

by Robert Balkin, Hector D. Ceniceros & Ruimeng Hu, JML 3 (2024), pp. 23-63.

Semi-Supervised Clustering of Sparse Graphs: Crossing the Information-Theoretic Threshold

by Junda Sheng & Thomas Strohmer, JML 3 (2024), pp. 64-106.

Approximation Results for Gradient Flow Trained Neural Networks

by Gerrit Welper, JML 3 (2024), pp. 107-175.

Mean-Field Neural Networks-Based Algorithms for McKean-Vlasov Control Problems

by Huyên Pham & Xavier Warin, JML 3 (2024), pp. 176-214.

Convergence of Stochastic Gradient Descent Schemes for Łojasiewicz-Landscapes

by Steffen Dereich & Sebastian Kassing, JML 3 (2024), pp. 245-281.

Fast Gradient Computation for Gromov-Wasserstein Distance

by Wei Zhang, Zihao Wang, Jie Fan, Hao Wu & Yong Zhang, JML 3 (2024), pp. 282-299.

Memory$^3$: Language Modeling with Explicit Memory

by Hongkang Yang, Zehao Lin, Wenjin Wang, Hao Wu, Zhiyu Li, Bo Tang, Wenqiang Wei, Jinbo Wang, Zeyun Tang, Shichao Song, Chenyang Xi, Yu Yu, Kai Chen, Feiyu Xiong, Linpeng Tang & Weinan E, JML 3 (2024), pp. 300-346.

Enhancing Accuracy in Deep Learning Using Random Matrix Theory

by Leonid Berlyand, Etienne Sandier, Yitzchak Shmalo & Lei Zhang, JML 3 (2024), pp. 347-412.

Variational Formulations of ODE-Net as a Mean-Field Optimal Control Problem and Existence Results

by Noboru Isobe & Mizuho Okumura, JML 3 (2024), pp. 413-444.

MAFE-Net: A Multi-Level Attention Feature Extraction Network for Pancreas Segmentation

by Jiawei Chen, Wenjie Chen, Zhipeng Zhu & Qi Ye, JML 3 (2024), pp. 445-463.

Reinforcement Learning Algorithm for Mixed Mean Field Control Games

by Andrea Angiuli, Nils Detering, Jean-Pierre Fouque, Mathieu Laurière & Jimin Lin, JML 2 (2023), pp. 108-137.

A Brief Survey on the Approximation Theory for Sequence Modelling

by Haotian Jiang, Qianxiao Li, Zhong Li & Shida Wang, JML 2 (2023), pp. 1-30.

Interpolating Between BSDEs and PINNs: Deep Learning for Elliptic and Parabolic Boundary Value Problems

by Nikolas Nüsken & Lorenz Richter, JML 2 (2023), pp. 31-64.

Batch Normalization Preconditioning for Stochastic Gradient Langevin Dynamics

by Susanna Lange, Wei Deng, Qiang Ye & Guang Lin, JML 2 (2023), pp. 65-82.

RNN-Attention Based Deep Learning for Solving Inverse Boundary Problems in Nonlinear Marshak Waves

by Di Zhao, Weiming Li, Wengu Chen, Peng Song & Han Wang, JML 2 (2023), pp. 83-107.

Why Self-Attention Is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries

by Chao Ma & Lexing Ying, JML 2 (2023), pp. 194-210.

A Local Convergence Theory for the Stochastic Gradient Descent Method in Non-Convex Optimization with Non-Isolated Local Minima

by Taehee Ko & Xiantao Li, JML 2 (2023), pp. 138-160.

Reinforcement Learning with Function Approximation: From Linear to Nonlinear

by Jihao Long & Jiequn Han, JML 2 (2023), pp. 161-193.

Efficient Anti-Symmetrization of a Neural Network Layer by Taming the Sign Problem

by Nilin Abrahamsen & Lin Lin, JML 2 (2023), pp. 211-240.

Prompt Engineering Through the Lens of Optimal Control

by Yifan Luo, Yiming Tang, Chengfeng Shen, Zhenan Zhou & Bin Dong, JML 2 (2023), pp. 241-258.

Embedding Inequalities for Barron-Type Spaces

by Lei Wu, JML 2 (2023), pp. 259-270.

A Mathematical Framework for Learning Probability Distributions

by Hongkang Yang, JML 1 (2022), pp. 373-431.

Approximation of Functionals by Neural Network Without Curse of Dimensionality

by Yahong Yang & Yang Xiang, JML 1 (2022), pp. 342-372.

The Cost-Accuracy Trade-Off in Operator Learning with Neural Networks

by Maarten V. de Hoop, Daniel Zhengyu Huang, Elizabeth Qian & Andrew M. Stuart, JML 1 (2022), pp. 299-341.

Bridging Traditional and Machine Learning-Based Algorithms for Solving PDEs: The Random Feature Method

by Jingrun Chen, Xurong Chi, Weinan E & Zhouwang Yang, JML 1 (2022), pp. 268-298.

Beyond the Quadratic Approximation: The Multiscale Structure of Neural Network Loss Landscapes

by Chao Ma, Daniel Kunin, Lei Wu & Lexing Ying, JML 1 (2022), pp. 247-267.

On the Existence of Global Minima and Convergence Analyses for Gradient Descent Methods in the Training of Deep Neural Networks

by Arnulf Jentzen & Adrian Riekert, JML 1 (2022), pp. 141-246.

DeePN$^2$: A Deep Learning-Based Non-Newtonian Hydrodynamic Model

by Lidong Fang, Pei Ge, Lei Zhang, Weinan E & Huan Lei, JML 1 (2022), pp. 114-140.

Embedding Principle: A Hierarchical Structure of Loss Landscape of Deep Neural Networks

by Yaoyu Zhang, Yuqing Li, Zhongwang Zhang, Tao Luo & Zhi-Qin John Xu, JML 1 (2022), pp. 60-113.

Ab-Initio Study of Interacting Fermions at Finite Temperature with Neural Canonical Transformation

by Hao Xie, Linfeng Zhang & Lei Wang, JML 1 (2022), pp. 38-59.

Perturbational Complexity by Distribution Mismatch: A Systematic Analysis of Reinforcement Learning in Reproducing Kernel Hilbert Space

by Jihao Long & Jiequn Han, JML 1 (2022), pp. 1-37.