AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition

Quan Xiao, Songtao Lu, Tianyi Chen

NeurIPS 2023 · Optimization › Nonconvex and smooth optimization · approach: Penalty and implicit-gradient bilevel methods · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use GALET instead of BOME for bilevel hyper-cleaningbilevel optimization · Hyper-cleaning on MNISTtest accuracy: 88.20 -> 90.20Improved
Use GALET instead of V-PBGDbilevel optimization · Hyper-cleaning on MNISTtest accuracy: 90.24 -> 90.20No clear effect
Use GALET instead of IAPTT-GMbilevel optimization · Hyper-cleaning on MNISTtest accuracy: 90.13 -> 90.20No clear effect
Vary upper-level stepsize alpha in {0.1,0.3,0.5,0.7,0.9} (ablation)GALET · Example 1 trajectoriestrajectory / optimality gapMixed
Vary shadow implicit gradient loops T in {1,5,50} and stepsize gamma in {0.1,0.5} (ablation)GALET · Example 1 trajectoriestrajectoryNo clear effect
Vary lower-level loops N in {1,5} and stepsize beta in {0.1,0.5,1,3} (ablation)GALET · Example 1 trajectoriestrajectoryNo clear effect
Use the proposed stationary measure instead of value-function KKT scoreGALET · Example 1convergence to 0Improved

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