Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD

26 June 2019

Papers citing "Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD"

5 / 5 papers shown

Title
Evolutionary algorithms as an alternative to backpropagation for supervised training of Biophysical Neural Networks and Neural ODEs James Hazelden Yuhan Helena Liu Eli Shlizerman E. Shea-Brown 52 2 0 17 Nov 2023
Towards Understanding Sharpness-Aware Minimization Maksym Andriushchenko Nicolas Flammarion AAML 35 134 0 13 Jun 2022
Tackling benign nonconvexity with smoothing and stochastic gradients Harsh Vardhan Sebastian U. Stich 31 8 0 18 Feb 2022
Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape Devansh Bisla Jing Wang A. Choromańska 27 34 0 20 Jan 2022
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 310 2,896 0 15 Sep 2016