vix.ing · top · new · best · stats · spec

Gradient-free prox-methods with inexact oracle for stochastic convex optimization problems on a simplex

2014/12/12 by Alexander Gasnikov, Gasnikov, Alexander, Anastasia Lagunovskaya +5
Computer Science · Engineering · Mathematics · #Advanced Optimization Algorithms Research #FOS: Mathematics #Optimization and Control (math.OC) #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques #math.OC

paper · pdf · doi:10.48550/arxiv.1412.3890

26 pages, in Russian, Avtomatika i Telemekhanika. 2016

openalex publication_date 2014/12/12 · arxiv created 2016/04/17 · arxiv updated 2016/04/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In the paper we show that euclidian randomization in some situations (i.e. for gradient-free method on a simplex) can be as good as the randomization on the unit sphere in 1-norm. That is on the simplex example we show that for gradient-free methods the choise of the prox-structure and the choise of a way of randomization have to be connected to each other. We demonstrate how it can be done in an optimal way. It is important that we consider inexact oracle.

Citations

Related