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 1502.06216math.OC
收藏

熵Wasserstein梯度流

Entropic Wasserstein Gradient Flows

Gabriel Peyré

摘要:

本文详细介绍了一种新的数值方法来近似梯度流的最优输运(即Wasserstein)指标。这些流动已被证明是有用的,以解决理论和数值模拟的非线性扩散方程,例如多孔介质或人群的演变。这些梯度流为这些演化定义了一个合适的弱解概念,并且可以用离散流以稳定的方式近似它们。这些离散流是根据Wasserstein度量的隐式Euler时间步进。这些方法的一个瓶颈是由每一步的分辨率引起的高计算负载。实际上,这对应于涉及到前一个向量的Wasserstein距离的凸优化问题的解决方案。在最近几项关于Wasserstein距离近似的工作之后,我们考虑由运输耦合的熵正则化引起的离散流。这种熵正则化允许我们用初始的Wasserstein保真度项来交换Kulback-Leibler散度,这在数值上更容易处理。我们将展示如何KL近端计划,特别是Dykstra的算法,可以用来计算每一步的正则化流。所得到的算法是快速,并行化和通用的,因为它只需要乘以吉布斯核。在均匀网格上离散化的欧几里得整环上,这对应于可以在近似线性时间内计算的线性滤波(例如,当$c$是平方欧几里德距离时的高斯滤波)。在更一般的域,如(可能是非凸的)形状或离散的三角形网格上的流形上,最近提出的最优输运的数值方案后,这吉布斯核乘法近似由一个短时间的热扩散。

英文摘要:

This article details a novel numerical scheme to approximate gradient flows for optimal transport (i.e. Wasserstein) metrics. These flows have proved useful to tackle theoretically and numerically non-linear diffusion equations that model for instance porous media or crowd evolutions. These gradient flows define a suitable notion of weak solutions for these evolutions and they can be approximated in a stable way using discrete flows. These discrete flows are implicit Euler time stepping according to the Wasserstein metric. A bottleneck of these approaches is the high computational load induced by the resolution of each step. Indeed, this corresponds to the resolution of a convex optimization problem involving a Wasserstein distance to the previous iterate. Following several recent works on the approximation of Wasserstein distances, we consider a discrete flow induced by an entropic regularization of the transportation coupling. This entropic regularization allows one to trade the initial Wasserstein fidelity term for a Kulback-Leibler divergence, which is easier to deal with numerically. We show how KL proximal schemes, and in particular Dykstra's algorithm, can be used to compute each step of the regularized flow. The resulting algorithm is both fast, parallelizable and versatile, because it only requires multiplications by a Gibbs kernel. On Euclidean domains discretized on an uniform grid, this corresponds to a linear filtering (for instance a Gaussian filtering when $c$ is the squared Euclidean distance) which can be computed in nearly linear time. On more general domains, such as (possibly non-convex) shapes or on manifolds discretized by a triangular mesh, following a recently proposed numerical scheme for optimal transport, this Gibbs kernel multiplication is approximated by a short-time heat diffusion.

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。

↑