Back to Search
Start Over
Stochastic intermediate gradient method for convex optimization problems.
- Source :
- Doklady Mathematics; Mar2016, Vol. 93 Issue 2, p148-151, 4p
- Publication Year :
- 2016
-
Abstract
- New first-order methods are introduced for solving convex optimization problems from a fairly broad class. For composite optimization problems with an inexact stochastic oracle, a stochastic intermediate gradient method is proposed that allows using an arbitrary norm in the space of variables and a prox-function. The mean rate of convergence of this method and the probability of large deviations from this rate are estimated. For problems with a strongly convex objective function, a modification of this method is proposed and its rate of convergence is estimated. The resulting estimates coincide, up to a multiplicative constant, with lower complexity bounds for the class of composite optimization problems with an inexact stochastic oracle and for all usually considered subclasses of this class. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10645624
- Volume :
- 93
- Issue :
- 2
- Database :
- Complementary Index
- Journal :
- Doklady Mathematics
- Publication Type :
- Academic Journal
- Accession number :
- 115423412
- Full Text :
- https://doi.org/10.1134/S1064562416020071