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 2309.09134cs.DScs.CCcs.DMcs.LG
收藏

全变差距离与概率推断的交汇

Total Variation Distance Meets Probabilistic Inference

National University of Singapore(新加坡国立大学);Indian Institute of Technology Kanpur(坎普尔印度理工学院);University of Toronto(多伦多大学);Iowa State University(爱荷华州立大学);University of Nebraska-Lincoln(内布拉斯加大学林肯分校)

Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel, Dimitrios Myrisiotis, A. Pavan, N. V. Vinodchandran

AI总结:

本文通过将全变差距离估计归约到有向图模型上的概率推断,首次为小树宽贝叶斯网络上的同结构分布提出了估计TV距离的完全多项式随机近似方案,并引入了高维分布的部分耦合新概念。

摘要:

本文在全变差(TV)距离估计与概率推断之间建立了一种新颖的联系。具体而言,我们提出了一种高效且保持结构的归约方法,将TV距离的相对近似归约到有向图模型上的概率推断。该归约方法带来了一个完全多项式随机近似方案(FPRAS),用于在任意一类存在高效概率推断算法的贝叶斯网络上估计具有相同结构分布之间的TV距离。特别地,它带来了一个FPRAS,用于估计定义在具有小树宽的公共贝叶斯网络上的分布之间的TV距离。在此工作之前,此类近似方案仅存在于估计乘积分布之间的TV距离。我们的方法采用了一种新的高维分布“部分”耦合概念,这可能具有独立的研究意义。

英文摘要:

In this paper, we establish a novel connection between total variation (TV) distance estimation and probabilistic inference. In particular, we present an efficient, structure-preserving reduction from relative approximation of TV distance to probabilistic inference over directed graphical models. This reduction leads to a fully polynomial randomized approximation scheme (FPRAS) for estimating TV distances between same-structure distributions over any class of Bayes nets for which there is an efficient probabilistic inference algorithm. In particular, it leads to an FPRAS for estimating TV distances between distributions that are defined over a common Bayes net of small treewidth. Prior to this work, such approximation schemes only existed for estimating TV distances between product distributions. Our approach employs a new notion of $partial$ couplings of high-dimensional distributions, which might be of independent interest.

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。

↑