Efficiently escaping saddle points in bilevel optimization

MaRDI QIDQ6982706zbMATH OpenFDO

Authors Minhui Huang, Xuxing Chen, Kaiyi Ji, Shiqian Ma, Lifeng Lai

Publication date 16 May 2025

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/22-0136.html

zbMATH Keywords

bilevel optimizationinexact NEONlocal minimax pointminimax problemsaddle point

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Convex programming (90C25) Nonconvex programming, global optimization (90C26)

Cites work

• A trust region algorithm with a worst-case iteration complexity of \(\mathcal{O}(\epsilon ^{-3/2})\) for nonconvex optimization
• Accelerated methods for nonconvex optimization
• Classification model selection via bilevel programming
• Cubic regularization of Newton method and its global performance
• Finding approximate local minima faster than gradient descent
• scientific article; zbMATH DE number 7625182 (Why is no real title available?)
• Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications
• Introductory lectures on convex optimization. A basic course.
• Mathematical Programs with Optimization Problems in the Constraints
• On Nonconvex Optimization for Machine Learning

Cited in

(1)

• Near-optimal nonconvex-strongly-convex bilevel optimization with fully first-order oracles

This page was built for publication: Efficiently escaping saddle points in bilevel optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6982706)