Abstract:Offline multi-objective optimization (MOO) aims to recover Pareto-optimal designs given a finite, static dataset. Recent generative approaches, including diffusion models, show strong performance under hypervolume, yet their behavior under other established MOO metrics is less understood. We show that generative methods systematically underperform evolutionary alternatives with respect to other metrics, such as generational distance. We relate this failure mode to the offline-frontier shift, i.e., the displacement of the offline dataset from the Pareto front, which acts as a fundamental limitation in offline MOO. We argue that overcoming this limitation requires out-of-distribution sampling in objective space (via an integral probability metric) and empirically observe that generative methods remain conservatively close to the offline objective distribution. Our results position offline MOO as a distribution-shift--limited problem and provide a diagnostic lens for understanding when and why generative optimization methods fail.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2602.11126 [cs.LG] |
| (or arXiv:2602.11126v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.11126 arXiv-issued DOI via DataCite |
From: Stephanie Holly [view email]
[v1]
Wed, 11 Feb 2026 18:38:40 UTC (354 KB)
[v2]
Tue, 12 May 2026 09:27:34 UTC (354 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。