Accelerated Gradient-Free Optimization Methods with a Non-Euclidean Proximal Operator
- Авторы: Vorontsova E.A.1,2, Gasnikov A.V.3,4,5, Gorbunov E.A.3, Dvurechenskii P.E.6
-
Учреждения:
- 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
- Выпуск: Том 80, № 8 (2019)
- Страницы: 1487-1501
- Раздел: 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
Цитировать
Аннотация
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.
Об авторах
E. Vorontsova
Far Eastern Federal University; Université Grenoble Alps
Автор, ответственный за переписку.
Email: vorontsovaea@gmail.com
Россия, Vladivostok; Grenoble
A. Gasnikov
Moscow Institute of Physics and Technology; National Research University Higher School of Economics; Caucasus Mathematical Center
Автор, ответственный за переписку.
Email: gasnikov@yandex.ru
Россия, Moscow; Moscow; Maikop, Republic of Adygea
E. Gorbunov
Moscow Institute of Physics and Technology
Автор, ответственный за переписку.
Email: ed-gorbunov@yandex.ru
Россия, Moscow
P. Dvurechenskii
Weierstrass Institute for Applied Analysis and Stochastics
Автор, ответственный за переписку.
Email: pavel.dvurechensky@gmail.com
Германия, Berlin
Дополнительные файлы
