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 2310.14522math.OCcs.NAmath.NA
收藏

基于核的方法用于施罗德inger桥

A kernel-based method for Schrödinger bridges

Institute of Science Tokyo(东京科学大学)

Yumiharu Nakano

AI总结:

本文提出基于核的方法解决施罗德inger桥问题,通过Mckean-Vlasov随机控制问题建模,并采用神经SDE深度学习算法进行求解,通过实验验证了方法的有效性。

摘要:

我们通过一系列Mckean-Vlasov随机控制问题来表征施罗德inger桥问题,这些问题没有终端时间分布约束。为此,我们利用概率测度的希尔伯特空间嵌入理论,并将约束描述为由最大均值差异定义的惩罚项。在给定初始和终端时间分布以及底层扩散过程的温和条件下,由ε最优控制产生的状态过程的概率律序列收敛到施罗德inger问题的唯一解。我们提出了一种基于神经SDE的深度学习算法用于Mckean-Vlasov随机控制问题。几个数值实验验证了我们的方法。

英文摘要:

We characterize the Schrödinger bridge problems by a family of Mckean-Vlasov stochastic control problems with no terminal time distribution constraint. In doing so, we use the theory of Hilbert space embeddings of probability measures and then describe the constraint as penalty terms defined by the maximum mean discrepancy in the control problems. A sequence of the probability laws of the state processes resulting from $ε$-optimal controls converges to a unique solution of the Schrödinger's problem under mild conditions on given initial and terminal time distributions and an underlying diffusion process. We propose a neural SDE based deep learning algorithm for the Mckean-Vlasov stochastic control problems. Several numerical experiments validate our methods.

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。

↑