arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.03294math.OC
收藏

平均系统上的薛定谔桥

Schrodinger Bridge over Averaged Systems

Daniel Owusu Adu, Yongxin Chen

AI总结:

针对受参数扰动的系统集合,本文用路径积分方法研究鲁棒薛定谔桥,证明最优控制为依赖过去与当前噪声的非马尔可夫随机前馈控制,并给出分布鲁棒形变结论。

摘要:

我们考虑一个薛定谔桥问题,其中马尔可夫过程受到参数扰动,从而形成一个系统集合。我们的目标是利用对参数扰动具有鲁棒性的控制,将该集合从初始分布引导至最终分布。借助路径积分形式,我们证明最优控制是一种非马尔可夫策略,具体而言是一种随机前馈控制,它依赖于过去和当前的噪声。这种与薛定谔桥问题既有策略的意外偏离,凸显了系统动力学中存在的复杂相互关系。从最优传输的角度来看,我们工作的一个重要副产品是证明了当分布的演化受到参数扰动时,可以利用随机前馈控制将该分布鲁棒地变形到期望的最终状态。

英文摘要:

We consider a Schrödinger bridge problem where the Markov process is subject to parameter perturbations, forming an ensemble of systems. Our objective is to steer this ensemble from the initial distribution to the final distribution using controls robust to the parameter perturbations. Utilizing the path integral formalism, we demonstrate that the optimal control is a non-Markovian strategy, specifically a stochastic feedforward control, which depends on past and present noise. This unexpected deviation from established strategies for Schrödinger bridge problems highlights the intricate interrelationships present in the system's dynamics. From the perspective of optimal transport, a significant by-product of our work is the demonstration that, when the evolution of a distribution is subject to parameter perturbations, it is possible to robustly deform the distribution to a desired final state using stochastic feedforward controls.

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。

↑