Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case


Дәйексөз келтіру

Толық мәтін

Ашық рұқсат Ашық рұқсат
Рұқсат жабық Рұқсат берілді
Рұқсат жабық Тек жазылушылар үшін

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.

Авторлар туралы

A. Gasnikov

Moscow Institute of Physics and Technology (State University); Institute for Information Transmission Problems (Kharkevich Institute)

Хат алмасуға жауапты Автор.
Email: gasnikov@yandex.ru
Ресей, Moscow; Moscow

E. Krymova

Institute for Information Transmission Problems (Kharkevich Institute)

Email: gasnikov@yandex.ru
Ресей, Moscow

A. Lagunovskaya

Keldysh Institute of Applied Mathematics; Moscow Institute of Physics and Technology (State University)

Email: gasnikov@yandex.ru
Ресей, Moscow; Moscow

I. Usmanova

Moscow Institute of Physics and Technology (State University); Institute for Information Transmission Problems (Kharkevich Institute)

Email: gasnikov@yandex.ru
Ресей, Moscow; Moscow

F. Fedorenko

Moscow Institute of Physics and Technology (State University)

Email: gasnikov@yandex.ru
Ресей, Moscow

Қосымша файлдар

Қосымша файлдар
Әрекет
1. JATS XML

© Pleiades Publishing, Ltd., 2017