Accelerated Gradient-Free Optimization Methods with a Non-Euclidean Proximal Operator
Accelerated Gradient-Free Optimization Methods with a Non-Euclidean Proximal Operator
复制标题
使用非欧几里得近端算子的加速无梯度优化方法
DOI:
10.1134/s0005117919080095
复制
发表时间:
2019
影响因子:
0.7
通讯作者:
Pavel E. Dvurechenskii
中科院分区:
文献类型:
--
作者:
E. Vorontsova;A. Gasnikov;Eduard A. Gorbunov;Pavel E. Dvurechenskii
We propose an accelerated gradient-free method with a non-Euclidean proximal operator associated with thep-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.