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

DOI10.1134/S0005117919080095MaRDI QIDQ2289040zbMATH OpenOpenAlexFDO

Authors Evgeniya A. Vorontsova, Alexander V. Gasnikov, É. A. Gorbunov, 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

accelerated optimization methodsconvex optimizationinaccurate oraclenon-Euclidean proximal operatornon-gradient methodsprox-structure

Mathematics Subject Classification ID

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

Recommendations

• Accelerated directional search with non-Euclidean prox-structure
• Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex
• Projection-free accelerated method for convex optimization
• A note on the (accelerated) proximal gradient method for composite convex optimization
• Generalized Nesterov's accelerated proximal gradient algorithms with convergence rate of order o(1/k^2)

Cites work

• Accelerated directional search with non-Euclidean prox-structure
• Deep learning
• scientific article; zbMATH DE number 3850830 (Why is no real title available?)
• scientific article; zbMATH DE number 3790207 (Why is no real title available?)
• scientific article; zbMATH DE number 3388498 (Why is no real title available?)
• Introduction to Stochastic Search and Optimization
• Learning representations by back-propagating errors
• Linear coupling: an ultimate unification of gradient and mirror descent
• 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
• Random gradient-free minimization of convex functions

Cited in

(9)

• An accelerated directional derivative method for smooth stochastic convex optimization
• Oracle complexity separation in convex optimization
• Accelerated directional search with non-Euclidean prox-structure
• Gradient-Free Methods with Inexact Oracle for Convex-Concave Stochastic Saddle-Point Problem
• An accelerated method for derivative-free smooth stochastic convex optimization
• An accelerated proximal gradient method for multiobjective optimization
• Accelerated gradient methods combining Tikhonov regularization with geometric damping driven by the Hessian
• First-order methods for convex optimization
• Unifying framework for accelerated randomized methods in convex optimization

Describes a project that uses

Uses Software

• BRENT
• ACDS
• GitHub

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2289040)