发现生成式多目标优化在数据分布偏移下表现不佳，提出诊断新视角。
The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization
- 识别出离线优化中的前沿偏移问题，导致生成方法性能下降。
- 在生成距离等指标上，生成方法显著落后于进化算法。
- 适合研究生成模型局限性或优化算法设计的学者参考。
离线多目标优化（MOO）旨在从有限静态数据集中恢复帕累托最优设计。近年来，生成方法（如扩散模型）在超体积指标上表现良好，但在其他经典MOO指标下的行为尚不明确。本文发现，生成方法在生成距离等指标上系统性地弱于进化算法。我们将其归因于离线前沿偏移现象，即离线数据集偏离帕累托前沿，成为离线MOO的根本限制。我们认为克服此限制需在目标空间中进行分布外采样（通过积分概率度量），并实证观察到生成方法仍保守地贴近离线目标分布。研究将离线MOO定位为分布偏移受限问题，并提供理解生成优化方法失效的诊断视角。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。