PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks

6 October 2022

Papers citing "PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks"

5 / 5 papers shown

Title
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions Arthur Jacot 34 24 0 29 Sep 2022
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions Aaron Mishkin Arda Sahiner Mert Pilanci OffRL 73 30 0 02 Feb 2022
Training Structured Neural Networks Through Manifold Identification and Variance Reduction Zih-Syuan Huang Ching-pei Lee AAML 38 9 0 05 Dec 2021
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics D. Kunin Javier Sagastuy-Breña Surya Ganguli Daniel L. K. Yamins Hidenori Tanaka 99 77 0 08 Dec 2020
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 114 577 0 27 Feb 2015