← Search

Jiulin Wang

2 accepted papers

2024

Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds

NeurIPS 2024poster

This paper investigates simple bilevel optimization problems where we minimize a convex upper-level objective over the optimal solution set of a convex lower-level objective. Existing methods for such problems either only guarantee asymptotic convergence, have slow sublinear rates, or require strong…

Cited by 4SourcePDFScholar