arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1601.04891math.PRmath.OC
收藏

Wasserstein积空间上的随机控制、熵插值和梯度流

Stochastic control, entropic interpolation and gradient flows on Wasserstein product spaces

Yongxin Chen, Tryphon Georgiou, Michele Pavon

摘要:

自90年代初以来,人们已经观察到,薛定谔桥问题可以用非典型边界约束的随机控制问题来表示。这反过来又有一个流体动力学对应,其中概率密度流表示给定的初始和最终边缘之间的熵插值。在零噪声极限下,这种熵插值在适当的意义上收敛于最优质量输运(OMT)的位移插值。考虑Wasserstein空间${\cal W}_2$中两条绝对连续的曲线,研究了有限时间区间上${\cal W}_2\times {\cal W}_2$上相对熵的演化.因此,这项研究不同于以前的工作,在OMT理论有关相对熵从一个固定的(往往是平衡)分布(密度)。本文导出了Wasserstein积空间上的梯度流。我们发现这两个分量的通量是相反的显着性质。把“最速下降“代入相对熵的演化中,我们得到了一个新的公式:两个流以比同一个福克-普朗克方程的两个解更快的速度相互接近。然后,我们研究的相对熵的演变的情况下,不受控制的控制扩散。在薛定谔桥问题的两种特殊情况下,我们证明了这样的相对熵可以是单调递减的或单调递增的。

英文摘要:

Since the early nineties, it has been observed that the Schroedinger bridge problem can be formulated as a stochastic control problem with atypical boundary constraints. This in turn has a fluid dynamic counterpart where the flow of probability densities represents an entropic interpolation between the given initial and final marginals. In the zero noise limit, such entropic interpolation converges in a suitable sense to the displacement interpolation of optimal mass transport (OMT). We consider two absolutely continuous curves in Wasserstein space ${\cal W}_2$ and study the evolution of the relative entropy on ${\cal W}_2\times {\cal W}_2$ on a finite time interval. Thus, this study differs from previous work in OMT theory concerning relative entropy from a fixed (often equilibrium) distribution (density). We derive a gradient flow on Wasserstein product space. We find the remarkable property that fluxes in the two components are opposite. Plugging in the "steepest descent" into the evolution of the relative entropy we get what appears to be a new formula: The two flows approach each other at a faster rate than that of two solutions of the same Fokker-Planck. We then study the evolution of relative entropy in the case of uncontrolled-controlled diffusions. In two special cases of the Schroedinger bridge problem, we show that such relative entropy may be monotonically decreasing or monotonically increasing.

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。

↑