The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization

Stephanie Holly, Alexandru-Ciprian Zavoianu, Siegfried Silber, Sepp Hochreiter, Werner Zellinger

Keywords: Offline multi-objective optimization, Generative modeling, Multi-objective metrics, Distribution shift

TL;DR: This work evaluates generative methods for offline multi-objective optimization beyond hypervolume, revealing failures driven by offline data limitations and insufficient out-of-distribution exploration.

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$\textendash$limited problem and provide a diagnostic lens for understanding when and why generative optimization methods fail.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Style Files: I have used the style files.

Submission Number: 100