Search Results

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

  Chao Ma, Daniel Kunin, Lei Wu, Lexing Ying

  2022-09-22

  39410 4502 Pages:247-267 Open-access

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

  Yaoyu Zhang, Yuqing Li, Zhongwang Zhang, Tao Luo, Zhi-Qin John Xu

  2024-03-21

  80496 4499 Pages:60-113 Open-access

• Spectral Neural Networks: Approximation Theory and Optimization Landscape

  Chenghui Li, Rishi Sonthalia, Nicolás García Trillos

  2026-01-06

  123 206

• Stochastic Operator Network: A Stochastic Maximum Principle Based Approach to Operator Learning

  Ryan Bausback, Jingqiao Tang, Lu Lu, Feng Bao, Phuoc-Toan Huynh

  2026-01-28

  109 46

• Batch Normalization Preconditioning for Stochastic Gradient Langevin Dynamics

  Susanna Lange, Wei Deng, Qiang Ye, Guang Lin

  2024-03-21

  33598 4465 Pages:65-82 Open-access

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

  Noboru Isobe, Mizuho Okumura

  2024-11-07

  17828 2123 Pages:413-444 Open-access

• On the Existence of Optimal Shallow Feedforward Networks with ReLU Activation

  Steffen Dereich, Sebastian Kassing

  2024-03-21

  25883 2930 Pages:1-22 Open-access

• Enhancing Accuracy in Deep Learning Using Random Matrix Theory

  Leonid Berlyand, Etienne Sandier, Yitzchak Shmalo, Lei Zhang

  2024-11-07

  19023 2480 Pages:347-412 Open-access