@inproceedings{f088a84aca5d432ba547e11f79fb71a4,
title = "Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent",
abstract = "As part of the effort to understand implicit bias of gradient descent in overparametrized models, several results have shown how the training trajectory on the overparametrized model can be understood as mirror descent on a different objective. The main result here is a characterization of this phenomenon under a notion termed commuting parametrization, which encompasses all the previous results in this setting. It is shown that gradient flow with any commuting parametrization is equivalent to continuous mirror descent with a related Legendre function. Conversely, continuous mirror descent with any Legendre function can be viewed as gradient flow with a related commuting parametrization. The latter result relies upon Nash's embedding theorem.",
author = "Zhiyuan Li and Tianhao Wang and Lee, {Jason D.} and Sanjeev Arora",
note = "Publisher Copyright: {\textcopyright} 2022 Neural information processing systems foundation. All rights reserved.; 36th Conference on Neural Information Processing Systems, NeurIPS 2022 ; Conference date: 28-11-2022 Through 09-12-2022",
year = "2022",
language = "English (US)",
series = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
editor = "S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh",
booktitle = "Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022",
}