AI Paper Atlas

Research map / Optimization / Optimizers

BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach

Bo Liu, Mao Ye, Stephen Wright, Peter Stone, qiang liu

NeurIPS 2022 · Optimization › Optimizers · approach: Hypergradient bilevel optimization · 6 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 BOME instead of ITD in CTNCTN · PMNISTACCImproved
Use BOME instead of ITD in CTNCTN · PMNISTNBTImproved
Use BOME instead of BVFSM in CTNCTN · PMNISTFTHurt
Use BOME instead of ITD in CTNCTN · Split CIFARACCImproved
Use BOME instead of ITD in CTNCTN · Split CIFARNBTImproved
Use BOME instead of BVFSM in CTNCTN · Split CIFARFTHurt
Vary inner-loop steps T (including T=1) (ablation)BOME · Toy coreset; data hyper-cleaning; learnable regularizationperformanceNo clear effect
Vary control coefficient η (ablation)BOME · Toy coreset; other reported experimentsperformanceNo clear effect
Vary inner step size α relative to outer step size ξ (ablation)BOME · Data hyper-cleaning; learnable regularizationperformanceNo clear effect
Use φ=ηq̂ instead of φ=η||∇q̂||² (ablation)BOME · Data hyper-cleaning; learnable regularizationperformanceNo clear effect

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