Convergence Rate of O(1/k) for Optimistic Gradient and Extragradient Methods in Smooth Convex-Concave Saddle Point Problems

Convergence Rate of O(1/k) for Optimistic Gradient and Extragradient Methods in Smooth Convex-Concave Saddle Point Problems

© 2020 Society for Industrial and Applied Mathematics We study the iteration complexity of the optimistic gradient descent-ascent (OGDA) method and the extragradient (EG) method for finding a saddle point of a convex-concave unconstrained min-max problem. To do so, we first show that both OGDA and E...

Full description

Bibliographic Details
Main Authors: Mokhtari, Aryan, Ozdaglar, Asuman E, Pattathil, Sarath
Other Authors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Format: Article
Language:English
Published: Society for Industrial & Applied Mathematics (SIAM) 2022
Online Access:https://hdl.handle.net/1721.1/143825

Internet

https://hdl.handle.net/1721.1/143825

Similar Items