arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.08319math.OCmath.PR
收藏

多边缘薛定谔桥

Multi-marginal Schrodinger bridges

Yongxin Chen, Giovanni Conforti, Tryphon T. Georgiou, Luigia Ripani

摘要:

我们考虑的问题,以确定最有可能的流量在相空间,(惯性)粒子的随机强迫下,这是在协议的空间(边际)分布,指定在一组点的时间。提出的问题推广了经典的薛定谔桥问题(SBP),该问题试图插值两个指定的端点边缘分布的随机激励驱动的过阻尼粒子。虽然我们将我们的分析限制在粒子的二阶动力学,但数据代表了部分(即,仅位置)有关{ \em多个}时间点的流量的信息。在SBP中,所寻求的解决方案代表了路径空间上的概率律,该概率律最接近统一先验,同时与给定的边缘一致。我们接近这个问题作为一个最优控制问题,以最小化的行动积分一la Benamou-Brenier,并推导出一个时间对称的制定,其中包括一个Fisher信息项的速度场。我们强调我们的问题的关系,最近的测量值样条在Wasserstein空间,这是类似于SBP和最优质量传输(OMT)之间。两者之间的联系提供了一个类似Sinkhorn的方法来计算测度值样条。我们设想,如本文所寻求的测量之间的插值将在信号/图像处理以及在数据具有时间维度的情况下的数据科学中具有广泛的应用。

英文摘要:

We consider the problem to identify the most likely flow in phase space, of (inertial) particles under stochastic forcing, that is in agreement with spatial (marginal) distributions that are specified at a set of points in time. The question raised generalizes the classical Schrodinger Bridge Problem (SBP) which seeks to interpolate two specified end-point marginal distributions of overdamped particles driven by stochastic excitation. While we restrict our analysis to second-order dynamics for the particles, the data represents partial (i.e., only positional) information on the flow at {\em multiple} time-points. The solution sought, as in SBP, represents a probability law on the space of paths this closest to a uniform prior while consistent with the given marginals. We approach this problem as an optimal control problem to minimize an action integral a la Benamou-Brenier, and derive a time-symmetric formulation that includes a Fisher information term on the velocity field. We underscore the relation of our problem to recent measure-valued splines in Wasserstein space, which is akin to that between SBP and Optimal Mass Transport (OMT). The connection between the two provides a Sinkhorn-like approach to computing measure-valued splines. We envision that interpolation between measures as sought herein will have a wide range of applications in signal/images processing as well as in data science in cases where data have a temporal dimension.

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。

↑