Mean-field analysis for heavy ball methods: Dropout-stability,
connectivity, and global convergence

Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence

13 October 2022

Vyacheslav Kungurtsev

Papers citing "Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence"

4 / 4 papers shown

Title
Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime Francesco Camilli D. Tieplova Eleonora Bergamin Jean Barbier 109 0 0 06 May 2025
Convex Analysis of the Mean Field Langevin Dynamics Atsushi Nitanda Denny Wu Taiji Suzuki MLT 61 64 0 25 Jan 2022
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics D. Kunin Javier Sagastuy-Breña Surya Ganguli Daniel L. K. Yamins Hidenori Tanaka 107 77 0 08 Dec 2020
A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights Weijie Su Stephen P. Boyd Emmanuel J. Candes 105 1,152 0 04 Mar 2015