Enviar artigo por via de e-mail Accelerated Gradient-Free Optimization Methods with a Non-Euclidean Proximal Operator
- Autores: Vorontsova E.A.1,2, Gasnikov A.V.3,4,5, Gorbunov E.A.3, Dvurechenskii P.E.6
-
Afiliações:
- Far Eastern Federal University
- Université Grenoble Alps
- Moscow Institute of Physics and Technology
- National Research University Higher School of Economics
- Caucasus Mathematical Center
- Weierstrass Institute for Applied Analysis and Stochastics
- Edição: Volume 80, Nº 8 (2019)
- Páginas: 1487-1501
- Seção: Optimization, System Analysis, and Operations Research
- URL: https://journals.rcsi.science/0005-1179/article/view/151140
- DOI: https://doi.org/10.1134/S0005117919080095
- ID: 151140
Citar
Acesso aberto
Acesso está concedido
Somente assinantes
Resumo
We propose an accelerated gradient-free method with a non-Euclidean proximal operator associated with the p-norm (1 ⩽ p ⩽ 2). We obtain estimates for the rate of convergence of the method under low noise arising in the calculation of the function value. We present the results of computational experiments.
Sobre autores
E. Vorontsova
Far Eastern Federal University; Université Grenoble Alps
Autor responsável pela correspondência
Email: vorontsovaea@gmail.com
Rússia, Vladivostok; Grenoble
A. Gasnikov
Moscow Institute of Physics and Technology; National Research University Higher School of Economics; Caucasus Mathematical Center
Autor responsável pela correspondência
Email: gasnikov@yandex.ru
Rússia, Moscow; Moscow; Maikop, Republic of Adygea
E. Gorbunov
Moscow Institute of Physics and Technology
Autor responsável pela correspondência
Email: ed-gorbunov@yandex.ru
Rússia, Moscow
P. Dvurechenskii
Weierstrass Institute for Applied Analysis and Stochastics
Autor responsável pela correspondência
Email: pavel.dvurechensky@gmail.com
Alemanha, Berlin
Arquivos suplementares
