Deep linear networks for regression are implicitly regularized towards flat minima

22 May 2024

Papers citing "Deep linear networks for regression are implicitly regularized towards flat minima"

5 / 5 papers shown

Title
Optimization Insights into Deep Diagonal Linear Networks Hippolyte Labarrière C. Molinari Lorenzo Rosasco S. Villa Cristian Vega 66 0 0 21 Dec 2024
The Optimization Landscape of SGD Across the Feature Learning Strength Alexander B. Atanasov Alexandru Meterez James B. Simon C. Pehlevan 43 2 0 06 Oct 2024
What Happens after SGD Reaches Zero Loss? --A Mathematical Framework Zhiyuan Li Tianhao Wang Sanjeev Arora MLT 83 98 0 13 Oct 2021
The large learning rate phase of deep learning: the catapult mechanism Aitor Lewkowycz Yasaman Bahri Ethan Dyer Jascha Narain Sohl-Dickstein Guy Gur-Ari ODL 153 232 0 04 Mar 2020
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 273 2,878 0 15 Sep 2016