|
Avtomatika i Telemekhanika, 2018, Issue 8, Pages 38–49
(Mi at14643)
|
|
|
|
This article is cited in 10 scientific papers (total in 10 papers)
Stochastic Systems
Gradient-free two-point methods for solving stochastic nonsmooth convex optimization problems with small non-random noises
A. S. Bayandinaab, A. V. Gasnikovacd, A. A. Lagunovskayaa a Moscow Institute of Physics and Technology (National Research University), Moscow, Russia
b Skolkovo University of Science and Technology, Moscow, Russia
c Higher School of Economics, Moscow, Russia
d Kharkevich Institute for Information Transmission Problems, Russian Academy of Sciences, Moscow, Russia
Abstract:
We study nonsmooth convex stochastic optimization problems with a two-point zero-order oracle, i.e., at each iteration one can observe the values of the function's realization at two selected points. These problems are first smoothed out with the well-known technique of double smoothing (B. T. Polyak) and then solved with the stochastic mirror descent method. We obtain conditions for the permissible noise level of a nonrandom nature exhibited in the computation of the function's realization for which the estimate on the method's rate of convergence is preserved.
Keywords:
mirror descent method, noise, stochastic optimization, gradient-free methods, double smoothing technique.
Citation:
A. S. Bayandina, A. V. Gasnikov, A. A. Lagunovskaya, “Gradient-free two-point methods for solving stochastic nonsmooth convex optimization problems with small non-random noises”, Avtomat. i Telemekh., 2018, no. 8, 38–49; Autom. Remote Control, 79:8 (2018), 1399–1408
Linking options:
https://www.mathnet.ru/eng/at14643 https://www.mathnet.ru/eng/at/y2018/i8/p38
|
Statistics & downloads: |
Abstract page: | 366 | Full-text PDF : | 38 | References: | 39 | First page: | 29 |
|