Отправить статью по E-mail Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex
- Авторы: Gasnikov A.V.1,2, Lagunovskaya A.A.1,3, Usmanova I.N.1,2, Fedorenko F.A.1
-
Учреждения:
- Moscow Institute of Physics and Technology (State University)
- Institute for Information Transmission Problems (Kharkevich Institute)
- Keldysh Institute of Applied Mathematics
- Выпуск: Том 77, № 11 (2016)
- Страницы: 2018-2034
- Раздел: Stochastic Systems, Queueing Systems
- URL: https://journals.rcsi.science/0005-1179/article/view/150480
- DOI: https://doi.org/10.1134/S0005117916110114
- ID: 150480
Цитировать
Открытый доступ
Доступ предоставлен
Только для подписчиков
Аннотация
In this paper we propose a modification of the mirror descent method for non-smooth stochastic convex optimization problems on the unit simplex. The optimization problems considered differ from the classical ones by availability of function values realizations. Our purpose is to derive the convergence rate of the method proposed and to determine the level of noise that does not significantly affect the convergence rate.
Об авторах
A. Gasnikov
Moscow Institute of Physics and Technology (State University); Institute for Information Transmission Problems (Kharkevich Institute)
Автор, ответственный за переписку.
Email: gasnikov@yandex.ru
Россия, Moscow; Moscow
A. Lagunovskaya
Moscow Institute of Physics and Technology (State University); Keldysh Institute of Applied Mathematics
Email: gasnikov@yandex.ru
Россия, Moscow; Moscow
I. Usmanova
Moscow Institute of Physics and Technology (State University); Institute for Information Transmission Problems (Kharkevich Institute)
Email: gasnikov@yandex.ru
Россия, Moscow; Moscow
F. Fedorenko
Moscow Institute of Physics and Technology (State University)
Email: gasnikov@yandex.ru
Россия, Moscow
Дополнительные файлы
