Accelerated Gradient Sliding for Minimizing a Sum of Functions

We propose a new way of justifying the accelerated gradient sliding of G. Lan, which allows one to extend the sliding technique to a combination of an accelerated gradient method with an accelerated variance reduction method. New optimal estimates for the solution of the problem of minimizing a sum...

Full description

Saved in:
Bibliographic Details
Published inDoklady. Mathematics Vol. 101; no. 3; pp. 244 - 246
Main Authors Dvinskikh, D. M., Omelchenko, S. S., Gasnikov, A. V., Tyurin, A. I.
Format Journal Article
LanguageEnglish
Published Moscow Pleiades Publishing 01.05.2020
Springer Nature B.V
Subjects
Computer Science
Mathematics
Mathematics and Statistics
Sliding
accelerated variance reduction methods
smooth strongly convex functions
accelerated gradient sliding of G. Lan
Online AccessGet full text

Cover

More Information
Summary:We propose a new way of justifying the accelerated gradient sliding of G. Lan, which allows one to extend the sliding technique to a combination of an accelerated gradient method with an accelerated variance reduction method. New optimal estimates for the solution of the problem of minimizing a sum of smooth strongly convex functions with a smooth regularizer are obtained.
ISSN:1064-5624
1531-8362
DOI:10.1134/S1064562420030084