A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer
Neural Networks

A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks

28 October 2022

Eric Vanden-Eijnden

Joan Bruna

Papers citing "A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks"

7 / 7 papers shown

Title
Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space Zhengdao Chen 28 1 0 03 Jul 2023
A Rainbow in Deep Network Black Boxes Florentin Guth Brice Ménard G. Rochette S. Mallat 17 10 0 29 May 2023
On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks Sebastian Neumayer Lénaïc Chizat M. Unser 25 2 0 31 Mar 2023
Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence Diyuan Wu Vyacheslav Kungurtsev Marco Mondelli 15 3 0 13 Oct 2022
Convex Analysis of the Mean Field Langevin Dynamics Atsushi Nitanda Denny Wu Taiji Suzuki MLT 59 64 0 25 Jan 2022
Optimization-Based Separations for Neural Networks Itay Safran Jason D. Lee 123 14 0 04 Dec 2021
Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach Grant M. Rotskoff Eric Vanden-Eijnden 59 118 0 02 May 2018