Improved complexities for stochastic conditional gradient methods under interpolation-like conditions

DOI10.1016/j.orl.2022.01.015OpenAlexW4225727086MaRDI QIDQ2670499

Tesi Xiao, Saeed Ghadimi, Krishnakumar Balasubramanian

Publication date: 11 March 2022

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.08167

zbMATH Keywords

overparametrizationoracle complexityzeroth-order optimizationstochastic conditional gradient

Mathematics Subject Classification ID

Operations research, mathematical programming (90-XX)

Uses Software

• Spearmint

Cites Work

• Unnamed Item
• Unnamed Item
• Conditional gradient algorithms for norm-regularized smooth convex optimization
• The gap function of a convex program
• Conditional gradient type methods for composite nonlinear and stochastic optimization
• Just interpolate: kernel ``ridgeless regression can generalize
• Random gradient-free minimization of convex functions
• Conditional Gradient Sliding for Convex Optimization
• An Extended Frank--Wolfe Method with “In-Face” Directions, and Its Application to Low-Rank Matrix Completion
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming

This page was built for publication: Improved complexities for stochastic conditional gradient methods under interpolation-like conditions