Vasin, Artem
[Verfasser:in];
Gasnikov, Alexander
[Verfasser:in];
Spokojnyj, Vladimir G.
[Verfasser:in]
;
Weierstraß-Institut für Angewandte Analysis und Stochastik
Stopping rules for accelerated gradient methods with additive noise in gradient
Beschreibung:
In this article, we investigate an accelerated first-order method, namely, the method of similar triangles, which is optimal in the class of convex (strongly convex) problems with a Lipschitz gradient. The paper considers a model of additive noise in a gradient and a Euclidean proxstructure for not necessarily bounded sets. Convergence estimates are obtained in the case of strong convexity and its absence, and a stopping criterion is proposed for not strongly convex problems.