arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.10986math.OCcs.NAmath.NA
收藏

熵正则化最优输运的区域分解

Domain decomposition for entropy regularized optimal transport

Mauro Bonafini, Bernhard Schmitzer

摘要:

研究了熵正则化下求解最优输运问题的Benamou区域分解算法。关键的观察是,正则化的变体收敛到全局最优解非常温和的假设下。我们证明了该算法的线性收敛的Kullback-Leibler发散和说明(可能非常慢)的速度与数值例子。对于具有足够几何结构的问题(例如图像之间的Wasserstein距离),我们期望更快的收敛。然后,我们讨论了重要方面的计算效率的实现,如自适应稀疏,粗到细的计划和并行化,铺平了道路,数值求解大规模的最优输运问题。我们表现出高效的数值性能计算的Wasserstein-2之间的距离的2D图像和观察,即使没有并行化,区域分解比较有利地应用一个单一的高效实现的Sinkhorn算法的运行时间,内存和解决方案的质量。

英文摘要:

We study Benamou's domain decomposition algorithm for optimal transport in the entropy regularized setting. The key observation is that the regularized variant converges to the globally optimal solution under very mild assumptions. We prove linear convergence of the algorithm with respect to the Kullback--Leibler divergence and illustrate the (potentially very slow) rates with numerical examples. On problems with sufficient geometric structure (such as Wasserstein distances between images) we expect much faster convergence. We then discuss important aspects of a computationally efficient implementation, such as adaptive sparsity, a coarse-to-fine scheme and parallelization, paving the way to numerically solving large-scale optimal transport problems. We demonstrate efficient numerical performance for computing the Wasserstein-2 distance between 2D images and observe that, even without parallelization, domain decomposition compares favorably to applying a single efficient implementation of the Sinkhorn algorithm in terms of runtime, memory and solution quality.

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。

↑