.png){kind=icon}
返回
The Data-Driven Schrodinger Bridge
.png){kind=icon}
OA
AI
DOI：10.1002/cpa.21975.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Erwin Schrodinger posed-and to a large extent solved-in 1931/32 the problem of finding the most likely random evolution between two continuous probability distributions. This article considers this problem in the case when only samples of the two distributions are available. A novel iterative procedure is proposed, inspired by Fortet-IPF-Sinkhorn type algorithms. Since only samples of the marginals are available, the new approach features constrained maximum likelihood estimation in place of the nonlinear boundary couplings, and importance sampling to propagate the functions phi and phi solving the Schrodinger system. This method mitigates the curse of dimensionality, compared to the introduction of grids, which in high dimensions lead to numerically unfeasible methods. The methodology is illustrated in two applications: entropic interpolation of two-dimensional Gaussian mixtures, and the estimation of integrals through a variation of importance sampling. (c) 2020 Wiley Periodicals LLC.
Keyword:
OPTIMAL TRANSPORT
MAXIMUM-ENTROPY
LEAST-SQUARES
CONVERGENCE
LIMIT
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
2.7
论文数:
1.5K
被引数:
1.1W
机构
引用论文
.png){kind=icon}
Changes in tropomyosin subunits and myosin light chains during development of chicken and rabbit straited muscles在鸡和兔骨骼肌发育过程中肌钙蛋白亚基和肌球蛋白轻链的变化
PREAI
分享收藏分享收藏分享收藏
查看更多内容