Accelerated gradient-free optimization methods with a non-Euclidean proximal operator

DOI10.1134/S0005117919080095zbMath1434.90144OpenAlexW2968969578MaRDI QIDQ2289040

Alexander V. Gasnikov, É. A. Gorbunov, Evgeniya A. Vorontsova, Pavel Dvurechensky

Publication date: 28 January 2020

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

Full work available at URL: https://doi.org/10.1134/s0005117919080095

zbMATH Keywords

convex optimizationaccelerated optimization methodsinaccurate oraclenon-Euclidean proximal operatornon-gradient methodsprox-structure

Mathematics Subject Classification ID

Convex programming (90C25) Derivative-free methods and methods using generalized derivatives (90C56)

Related Items (6)

Oracle complexity separation in convex optimization ⋮ An Accelerated Method for Derivative-Free Smooth Stochastic Convex Optimization ⋮ First-order methods for convex optimization ⋮ Unifying framework for accelerated randomized methods in convex optimization ⋮ An accelerated directional derivative method for smooth stochastic convex optimization ⋮ Gradient-Free Methods with Inexact Oracle for Convex-Concave Stochastic Saddle-Point Problem

Uses Software

• BRENT
• GitHub
• ACDS

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• 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
• Random gradient-free minimization of convex functions
• Introduction to Stochastic Search and Optimization
• Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent
• Learning representations by back-propagating errors

This page was built for publication: Accelerated gradient-free optimization methods with a non-Euclidean proximal operator