电邮这篇文章 Accelerated Gradient-Free Optimization Methods with a Non-Euclidean Proximal Operator
- 作者: Vorontsova E.A.1,2, Gasnikov A.V.3,4,5, Gorbunov E.A.3, Dvurechenskii P.E.6
-
隶属关系:
- 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
- 期: 卷 80, 编号 8 (2019)
- 页面: 1487-1501
- 栏目: 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
如何引用文章
开放存取
##reader.subscriptionAccessGranted##
订阅存取
详细
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.
作者简介
E. Vorontsova
Far Eastern Federal University; Université Grenoble Alps
编辑信件的主要联系方式.
Email: vorontsovaea@gmail.com
俄罗斯联邦, Vladivostok; Grenoble
A. Gasnikov
Moscow Institute of Physics and Technology; National Research University Higher School of Economics; Caucasus Mathematical Center
编辑信件的主要联系方式.
Email: gasnikov@yandex.ru
俄罗斯联邦, Moscow; Moscow; Maikop, Republic of Adygea
E. Gorbunov
Moscow Institute of Physics and Technology
编辑信件的主要联系方式.
Email: ed-gorbunov@yandex.ru
俄罗斯联邦, Moscow
P. Dvurechenskii
Weierstrass Institute for Applied Analysis and Stochastics
编辑信件的主要联系方式.
Email: pavel.dvurechensky@gmail.com
德国, Berlin
补充文件
