arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2008.03006math.OCcs.DScs.LGcs.NAmath.NA
收藏

结构多边际最优输运问题的多项式时间算法

Polynomial-time algorithms for Multimarginal Optimal Transport problems with structure

Massachusetts Institute of Technology(麻省理工学院)

Jason M. Altschuler, Enric Boix-Adsera

摘要:

多边际最优输运(MOT)由于在机器学习、统计学和科学中的应用而引起了极大的兴趣。然而,在大多数应用中,MOT的成功受到缺乏有效算法的严重限制。事实上,MOT一般需要边缘数k和它们的支持大小n的指数时间。本文发展了一个关于什么样的"结构"使MOT在poly(n,k)时间内可解的一般理论。我们开发了一个统一的算法框架,用于解决MOT在poly(n,k)的时间特征的“结构”,不同的算法需要在简单的变种的双重可行性预言。这个框架有几个好处。首先,它使我们能够表明,Sinkhorn算法,这是目前最流行的MOT算法,需要严格更多的结构比其他算法在poly(n,k)时间解决MOT。其次,我们的框架使得它更简单地开发一个给定的MOT问题的聚(n,k)时间算法。特别是,它是必要的和足够的(近似)解决双可行性预言-这是更适合于标准的算法技术。我们说明了这种易用性,通过开发poly(n,k)时间算法的三个一般类的MOT费用结构:(1)图形结构;(2)集优化结构;(3)低秩加稀疏结构。对于结构(1),我们恢复了已知的结果,Sinkhorn有poly(n,k)的运行时间;此外,我们提供了第一个poly(n,k)时间算法计算的解决方案,是精确的和稀疏的。对于结构(2)-(3),我们给出了第一个Poly(n,k)时间算法,即使是近似计算。这三种结构一起包含了MOT的许多(如果不是大多数的话)当前应用。

英文摘要:

Multimarginal Optimal Transport (MOT) has attracted significant interest due to applications in machine learning, statistics, and the sciences. However, in most applications, the success of MOT is severely limited by a lack of efficient algorithms. Indeed, MOT in general requires exponential time in the number of marginals k and their support sizes n. This paper develops a general theory about what "structure" makes MOT solvable in poly(n,k) time. We develop a unified algorithmic framework for solving MOT in poly(n,k) time by characterizing the "structure" that different algorithms require in terms of simple variants of the dual feasibility oracle. This framework has several benefits. First, it enables us to show that the Sinkhorn algorithm, which is currently the most popular MOT algorithm, requires strictly more structure than other algorithms do to solve MOT in poly(n,k) time. Second, our framework makes it much simpler to develop poly(n,k) time algorithms for a given MOT problem. In particular, it is necessary and sufficient to (approximately) solve the dual feasibility oracle -- which is much more amenable to standard algorithmic techniques. We illustrate this ease-of-use by developing poly(n,k) time algorithms for three general classes of MOT cost structures: (1) graphical structure; (2) set-optimization structure; and (3) low-rank plus sparse structure. For structure (1), we recover the known result that Sinkhorn has poly(n,k) runtime; moreover, we provide the first poly(n,k) time algorithms for computing solutions that are exact and sparse. For structures (2)-(3), we give the first poly(n,k) time algorithms, even for approximate computation. Together, these three structures encompass many -- if not most -- current applications of MOT.

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。

↑