Stochastic gradient descent introduces an effective landscape-dependent regularization favoring flat solutions

2 June 2022

Papers citing "Stochastic gradient descent introduces an effective landscape-dependent regularization favoring flat solutions"

2 / 2 papers shown

Title
High-entropy Advantage in Neural Networks' Generalizability Entao Yang Wei Wei Yue Shang Ge Zhang AI4CE 92 0 0 17 Mar 2025
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys Pratik Chaudhari A. Choromańska Stefano Soatto Yann LeCun Carlo Baldassi C. Borgs J. Chayes Levent Sagun R. Zecchina ODL 96 773 0 06 Nov 2016