Article
On Scaled Methods for Saddle Point Problems
arXiv
Document Type
Article
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. Copyright © 2022, The Authors. All rights reserved.
DOI
10.48550/arXiv.2206.08303
Publication Date
6-16-2022
Keywords
- Adaptive scaling,
- Hutchison,
- Machine learning problem,
- Saddle point problems,
- Scaled methods,
- Scalings,
- Machine learning,
- Machine Learning (cs.LG),
- Optimization and Control (math.OC)
Disciplines
Citation Information
A. Beznosikov, A. Alanov, D. Kovalev, M. Takac, and A. Gasnikov, "On Scaled Methods for Saddle Point Problems", 2022, arXiv:2206.08303
IR Deposit conditions: non-described
Preprint available on arXiv