arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2602.00737cs.LGcs.AI
收藏

基于帕累托条件的扩散模型用于离线多目标优化

Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization

Aalto University(阿尔托大学);Tampere University(塔尔库大学)

Jatan Shrestha, Santeri Heiskanen, Kari Hepola, Severi Rissanen, Pekka Jääskeläinen, Joni Pajarinen

AI总结:

基于帕累托条件的扩散模型用于离线多目标优化,通过条件采样解决离线多目标优化问题,提升泛化能力和任务一致性。

摘要:

多目标优化(MOO)在许多现实应用中出现,其中需要仔细平衡相互竞争的目标。在离线设置中,只有静态数据集可用,主要挑战是超越观察数据进行泛化。我们介绍了帕累托条件扩散(PCD),一种新的框架,将离线MOO作为条件采样问题进行建模。通过直接对期望的权衡进行条件,PCD避免了显式代理模型的需要。为了有效探索帕累托前沿,PCD采用了一种重新加权策略,专注于高性能样本,并采用参考方向机制,引导采样向训练数据之外的新、有前途的区域发展。在标准离线MOO基准上的实验表明,PCD实现了高度竞争性的性能,并且重要的是,在不同任务中表现出更大的一致性,优于现有离线MOO方法。

英文摘要:

Multi-objective optimization (MOO) arises in many real-world applications where trade-offs between competing objectives must be carefully balanced. In the offline setting, where only a static dataset is available, the main challenge is generalizing beyond observed data. We introduce Pareto-Conditioned Diffusion (PCD), a novel framework that formulates offline MOO as a conditional sampling problem. By conditioning directly on desired trade-offs, PCD avoids the need for explicit surrogate models. To effectively explore the Pareto front, PCD employs a reweighting strategy that focuses on high-performing samples and a reference-direction mechanism to guide sampling towards novel, promising regions beyond the training data. Experiments on standard offline MOO benchmarks show that PCD achieves highly competitive performance and, importantly, demonstrates greater consistency across diverse tasks than existing offline MOO approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑