Depth Without the Magic: Inductive Bias of Natural Gradient Descent

22 November 2021

Papers citing "Depth Without the Magic: Inductive Bias of Natural Gradient Descent"

4 / 4 papers shown

Title
Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks Adeyemi Damilare Adeoye Philipp Christian Petersen Alberto Bemporad 28 1 0 23 Apr 2024
Noise misleads rotation invariant algorithms on sparse targets Manfred K. Warmuth Wojciech Kotlowski Matt Jones Ehsan Amid 15 0 0 05 Mar 2024
Rethinking Gauss-Newton for learning over-parameterized models Michael Arbel Romain Menegaux Pierre Wolinski AI4CE 22 5 0 06 Feb 2023
Stochastic Training is Not Necessary for Generalization Jonas Geiping Micah Goldblum Phillip E. Pope Michael Moeller Tom Goldstein 89 72 0 29 Sep 2021