Отправить статью по E-mail Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
- Авторы: Gasnikov A.V.1,2, Krymova E.A.2, Lagunovskaya A.A.3,1, 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 78, № 2 (2017)
- Страницы: 224-234
- Раздел: Stochastic Systems, Queueing Systems
- URL: https://journals.rcsi.science/0005-1179/article/view/150534
- DOI: https://doi.org/10.1134/S0005117917020035
- ID: 150534
Цитировать
Открытый доступ
Доступ предоставлен
Только для подписчиков
Аннотация
In this paper the gradient-free modification of the mirror descent method for convex stochastic online optimization problems is proposed. The crucial assumption in the problem setting is that function realizations are observed with minor noises. The aim of this paper is to derive the convergence rate of the proposed methods and to determine a noise level which does not significantly affect the convergence rate.
Ключевые слова
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
E. Krymova
Institute for Information Transmission Problems (Kharkevich Institute)
Email: gasnikov@yandex.ru
Россия, Moscow
A. Lagunovskaya
Keldysh Institute of Applied Mathematics; Moscow Institute of Physics and Technology (State University)
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
