Gradient-free two-point methods for solving stochastic nonsmooth convex optimization problems with small non-random noises

DOI10.1134/S0005117918080039zbMath1398.93312OpenAlexW4246031696MaRDI QIDQ1616222

A. S. Bayandina, A. A. Lagunovskaya, Alexander V. Gasnikov

Publication date: 1 November 2018

Published in: Automation and Remote Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1134/s0005117918080039

zbMATH Keywords

noisestochastic optimizationmirror descent methoddouble smoothing techniquegradient-free methods

Mathematics Subject Classification ID

Applications of optimal control and differential games (49N90) Stochastic systems in control theory (general) (93E03)

Related Items (6)

An Accelerated Method for Derivative-Free Smooth Stochastic Convex Optimization ⋮ Gradient-free methods for non-smooth convex stochastic optimization with heavy-tailed noise on convex compact ⋮ An accelerated directional derivative method for smooth stochastic convex optimization ⋮ On the upper bound for the expectation of the norm of a vector uniformly distributed on the sphere and the phenomenon of concentration of uniform measure on the sphere ⋮ Accelerated directional search with non-Euclidean prox-structure ⋮ Noisy zeroth-order optimization for non-smooth saddle point problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Primal-dual subgradient methods for convex problems
• Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex
• Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
• Lectures on Modern Convex Optimization
• Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization
• An optimal algorithm for stochastic strongly-convex optimization
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems

This page was built for publication: Gradient-free two-point methods for solving stochastic nonsmooth convex optimization problems with small non-random noises