Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
- 作者: Gasnikov A.V.1,2, Krymova E.A.2, Lagunovskaya A.A.3,1, Usmanova I.N.1,2, Fedorenko F.A.1
-
隶属关系:
- Moscow Institute of Physics and Technology (State University)
- Institute for Information Transmission Problems (Kharkevich Institute)
- Keldysh Institute of Applied Mathematics
- 期: 卷 78, 编号 2 (2017)
- 页面: 224-234
- 栏目: Stochastic Systems, Queueing Systems
- URL: https://journals.rcsi.science/0005-1179/article/view/150534
- DOI: https://doi.org/10.1134/S0005117917020035
- ID: 150534
如何引用文章
详细
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.
作者简介
A. Gasnikov
Moscow Institute of Physics and Technology (State University); Institute for Information Transmission Problems (Kharkevich Institute)
编辑信件的主要联系方式.
Email: gasnikov@yandex.ru
俄罗斯联邦, Moscow; Moscow
E. Krymova
Institute for Information Transmission Problems (Kharkevich Institute)
Email: gasnikov@yandex.ru
俄罗斯联邦, Moscow
A. Lagunovskaya
Keldysh Institute of Applied Mathematics; Moscow Institute of Physics and Technology (State University)
Email: gasnikov@yandex.ru
俄罗斯联邦, Moscow; Moscow
I. Usmanova
Moscow Institute of Physics and Technology (State University); Institute for Information Transmission Problems (Kharkevich Institute)
Email: gasnikov@yandex.ru
俄罗斯联邦, Moscow; Moscow
F. Fedorenko
Moscow Institute of Physics and Technology (State University)
Email: gasnikov@yandex.ru
俄罗斯联邦, Moscow
补充文件
