arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08215cs.LGstat.ME
收藏

无分布鲁棒的函数空间预测-优化

Distribution-Free Robust Predict-Then-Optimize in Function Spaces

University of Michigan(密歇根大学)

Yash Patel, Ambuj Tewari

AI总结:

本文提出了一种无分布鲁棒的函数空间预测-优化方法,通过扩展符合预测到无限维空间,提升工程设计的鲁棒性。

摘要:

在工程设计工作流中快速求解偏微分方程的需求推动了神经代理模型的兴起。特别是,神经算子模型通过保留其参数的无限维函数形式,提供了一种离散化不变的代理。尽管提高了处理速度,此类方法缺乏准确性保证,不同于经典的数值PDE求解器。在这些可能被错误校准的代理下优化工程设计,存在产生在部署时表现不佳的设计的风险。类似地,在有限维设定中,对黑盒预测器进行自动决策也存在在模型校准不佳时产生次优性的风险。为此,出现了产生对抗鲁棒决策的方法,以在上游模型的不确定性估计下产生鲁棒决策。其中一种框架利用符合预测,一种无分布的后处理不确定性量化方法,因其与黑盒预测器的自然配对,提供这些估计。本文将此符合鲁棒决策方法扩展到无限维函数空间。我们首先将典型的符合预测保证从有限维空间扩展到无限维Sobolev空间。然后展示如何利用这种不确定性来鲁棒地制定工程设计任务,并表征由此产生的鲁棒最优设计的次优性。然后我们经验性地展示了我们的功能符合覆盖方法在多样化的PDE集合中的通用性,包括泊松方程和热方程,并展示了在量子态鉴别任务中这种鲁棒设计的显著改进。

英文摘要:

The need to rapidly solve PDEs in engineering design workflows has spurred the rise of neural surrogate models. In particular, neural operator models provide a discretization-invariant surrogate by retaining the infinite-dimensional, functional form of their arguments. Despite improved throughput, such methods lack guarantees on accuracy, unlike classical numerical PDE solvers. Optimizing engineering designs under these potentially miscalibrated surrogates thus runs the risk of producing designs that perform poorly upon deployment. In a similar vein, there is growing interest in automated decision-making under black-box predictors in the finite-dimensional setting, where a similar risk of suboptimality exists under poorly calibrated models. For this reason, methods have emerged that produce adversarially robust decisions under uncertainty estimates of the upstream model. One such framework leverages conformal prediction, a distribution-free post-hoc uncertainty quantification method, to provide these estimates due to its natural pairing with black-box predictors. We herein extend this line of conformally robust decision-making to infinite-dimensional function spaces. We first extend the typical conformal prediction guarantees over finite-dimensional spaces to infinite-dimensional Sobolev spaces. We then demonstrate how such uncertainty can be leveraged to robustly formulate engineering design tasks and characterize the suboptimality of the resulting robust optimal designs. We then empirically demonstrate the generality of our functional conformal coverage method across a diverse collection of PDEs, including the Poisson and heat equations, and showcase the significant improvement of such robust design in a quantum state discrimination task.

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。

↑