Translator Disclaimer
2014 Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization
Anatoli Juditsky, Yuri Nesterov
Stoch. Syst. 4(1): 44-80 (2014). DOI: 10.1214/10-SSY010

Abstract

We discuss non-Euclidean deterministic and stochastic algorithms for optimization problems with strongly and uniformly convex objectives. We provide accuracy bounds for the performance of these algorithms and design methods which are adaptive with respect to the parameters of strong or uniform convexity of the objective: in the case when the total number of iterations $N$ is fixed, their accuracy coincides, up to a logarithmic in $N$ factor with the accuracy of optimal algorithms.

Citation

Download Citation

Anatoli Juditsky. Yuri Nesterov. "Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization." Stoch. Syst. 4 (1) 44 - 80, 2014. https://doi.org/10.1214/10-SSY010

Information

Published: 2014
First available in Project Euclid: 18 September 2014

zbMATH: 1297.90097
MathSciNet: MR3353214
Digital Object Identifier: 10.1214/10-SSY010

Subjects:
Primary: 90C15
Secondary: 90C25

Rights: Copyright © 2014 INFORMS Applied Probability Society

JOURNAL ARTICLE
37 PAGES


SHARE
Vol.4 • No. 1 • 2014
Back to Top