AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Diversity-Driven Offline Multi-Objective Optimization via Nested Pareto Set Learning

Yiyi Zhu, Yaolin Wen, Xiang Xia, Xin An, Hanyi Si, Xiang Shu, Yangde Fu, Liang Dou, Hong Qian

ICML 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Multi-objective optimization · 0 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
add nested Pareto set learning (ablation)DOMOO · IN-1K/MOP7HV: 3.89 -> 4.48Improved
add nested Pareto set learning (ablation)DOMOO · RegexHV: 4.98 -> 6.52Improved
add accumulative risk control (ablation)DOMOO · RegexHV: 5.72 -> 6.52Improved
add accumulative risk control (ablation)DOMOO · MO-HopperHV: 5.49 -> 6.43Improved
add surrogate model generation (ablation)DOMOO · DTLZ3HV: 9.72 -> 10.63Improved
add surrogate model generation (ablation)DOMOO · MO-HopperHV: 6.30 -> 6.43Hurt
add Pareto set model generation (ablation)DOMOO · RegexHV: 3.68 -> 6.52Improved
add diversity-driven solution selection instead of HV selection (ablation)DOMOO · RegexHV: 5.25 -> 6.52Improved
add diversity-driven solution selection instead of HV selection (ablation)DOMOO · MO-HopperIGD_offline: 0.78 -> 0.58Improved
add diversity-driven solution selection instead of HV selection (ablation)DOMOO · IN-1K/MOP7HV: 4.43 -> 4.48No clear effect
add nested Pareto set learning (ablation)DOMOO · RegexIGD_offline: 1.04 -> 0.88Improved
use DOMOO instead of ParetoFlowoffline MOO · Off-MOO-Benchaverage HV rank: 10.19 -> 4.63Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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