Paper ID: 2206.08303

On Scaled Methods for Saddle Point Problems

Aleksandr Beznosikov, Aibek Alanov, Dmitry Kovalev, Martin Takáč, Alexander Gasnikov

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.

Submitted: Jun 16, 2022