An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes

5 July 2024

Papers citing "An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes"

6 / 6 papers shown

Title
Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation Robert M. Gower Guillaume Garrigos Nicolas Loizou Dimitris Oikonomou Konstantin Mishchenko Fabian Schaipp 31 0 0 02 Apr 2025
Loss Landscape Characterization of Neural Networks without Over-Parametrization Rustem Islamov Niccolò Ajroldi Antonio Orvieto Aurélien Lucchi 20 0 0 16 Oct 2024
Anticorrelated Noise Injection for Improved Generalization Antonio Orvieto Hans Kersting F. Proske Francis R. Bach Aurélien Lucchi 42 44 0 06 Feb 2022
L4: Practical loss-based stepsize adaptation for deep learning Michal Rolínek Georg Martius ODL 26 63 0 14 Feb 2018
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition Hamed Karimi J. Nutini Mark W. Schmidt 114 1,190 0 16 Aug 2016
A simpler approach to obtaining an O(1/t) convergence rate for the projected stochastic subgradient method Simon Lacoste-Julien Mark W. Schmidt Francis R. Bach 109 253 0 10 Dec 2012