Enviar artigo por via de e-mail Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex
- Autores: Gasnikov A.V.1,2, Lagunovskaya A.A.1,3, Usmanova I.N.1,2, Fedorenko F.A.1
-
Afiliações:
- Moscow Institute of Physics and Technology (State University)
- Institute for Information Transmission Problems (Kharkevich Institute)
- Keldysh Institute of Applied Mathematics
- Edição: Volume 77, Nº 11 (2016)
- Páginas: 2018-2034
- Seção: Stochastic Systems, Queueing Systems
- URL: https://journals.rcsi.science/0005-1179/article/view/150480
- DOI: https://doi.org/10.1134/S0005117916110114
- ID: 150480
Citar
Acesso aberto
Acesso está concedido
Somente assinantes
Resumo
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.
Sobre autores
A. Gasnikov
Moscow Institute of Physics and Technology (State University); Institute for Information Transmission Problems (Kharkevich Institute)
Autor responsável pela correspondência
Email: gasnikov@yandex.ru
Rússia, Moscow; Moscow
A. Lagunovskaya
Moscow Institute of Physics and Technology (State University); Keldysh Institute of Applied Mathematics
Email: gasnikov@yandex.ru
Rússia, Moscow; Moscow
I. Usmanova
Moscow Institute of Physics and Technology (State University); Institute for Information Transmission Problems (Kharkevich Institute)
Email: gasnikov@yandex.ru
Rússia, Moscow; Moscow
F. Fedorenko
Moscow Institute of Physics and Technology (State University)
Email: gasnikov@yandex.ru
Rússia, Moscow
Arquivos suplementares
