On Scaled Methods for Saddle Point Problems

Abstract
Methods with adaptive scaling of different features play a key role in solving saddle point problems, primarily due to Adam's popularity for solving adversarial machine learning problems, including GANS training. This paper carries out a theoretical analysis of the following scaling techniques for solving SPPs: the well-known Adam and RmsProp scaling and the newer AdaHessian and OASIS based on Hutchison approximation. We use the Extra Gradient and its improved version with negative momentum as the basic method. Experimental studies on GANs show good applicability not only for Adam, but also for other less popular methods.

Publisher
arXiv

arXiv
2206.08303

Additional Links
https://arxiv.org/pdf/2206.08303.pdf

Permanent link to this record