AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap Functions

Wei Yao, Haian Yin, Shangzhi Zeng, Jin Zhang

ICLR 2025 · Optimization › Nonconvex and smooth optimization · approach: Penalty and implicit-gradient bilevel methods · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a single-loop Hessian-free method for constrained bilevel optimization with general (nonlinear) lower-level constraints, using regularized gap functions.

Problem

Constrained bilevel optimization where existing methods are restricted to specific lower-level constraint types, such as linear constraints.

Approach

A single-loop, Hessian-free algorithm built on regularized gap functions that handles general lower-level constraints, extending beyond the linear-constraint settings of prior bilevel methods.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy