Using Taylor-approximated gradients to improve the Frank-Wolfe method for empirical risk minimization

DOI10.1137/22m1519286MaRDI QIDQ6579995

Robert M. Freund, Zikai Xiong

Publication date: 29 July 2024

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

zbMATH Keywords

computational complexityconvex optimizationlinear predictionempirical risk minimizationFrank-Wolfelinear minimization oracle

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Abstract computational complexity for mathematical programming problems (90C60) Nonconvex programming, global optimization (90C26)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• The landscape of empirical risk for nonconvex losses
• Generalized stochastic Frank-Wolfe algorithm with stochastic ``substitute gradient for structured convex optimization
• Conditional Gradient Sliding for Convex Optimization
• An Extended Frank--Wolfe Method with “In-Face” Directions, and Its Application to Low-Rank Matrix Completion
• Stochastic Conditional Gradient++: (Non)Convex Minimization and Continuous Submodular Maximization
• The Elements of Statistical Learning

This page was built for publication: Using Taylor-approximated gradients to improve the Frank-Wolfe method for empirical risk minimization