arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.10196cs.DScs.LGmath.STstat.TH
收藏

对数配分函数的量化变分逼近

Quantifying Variational Approximation for the Log-Partition Function

Massachusetts Institute of Technology(麻省理工学院)

Romain Cosson, Devavrat Shah

摘要:

变分近似,如平均场(MF)和树重加权(TRW),提供了一个计算效率的近似的一般图形模型的对数配分函数。TRW可证明提供了一个上限,但近似比通常没有量化。作为这项工作的主要贡献,我们提供了一种方法来量化的近似比通过底层图结构的属性。具体来说,我们认为,(一个变种)TRW产生的估计是在任何离散成对图形模型的真正的日志分区函数的因素$\frac{1}{\sqrt{κ(G)}}$在图$G$,其中$κ(G) \in (0,1]$捕获$G$是多远树结构与$κ(G) = 1$的树和$2/N$的完整的图在$N$顶点。因此,对于树,近似比为$1$,对于具有最大平均度$d$的任何图,近似比为$\sqrt{(d+1)/2}$,对于围长(最短圈)至少为$β\log N$的图,近似比为$\stackrel{β\to\infty}{\approx} 1+1/(2β)$。一般来说,$κ(G)$是与$G$相关的最大-最小问题的解,可以在多项式时间内对任何图进行评估。使用G的生成树上的均匀分布的样本,我们提供了一个近线性时间变量,该变量实现了近似比等于图的最小(跨边缘)有效电阻的平方根的倒数。我们将我们的结果连接到基于图划分的近似方法,从而提供了一个统一的视角。关键词:变分推理,对数-划分函数,生成树多面体,最小有效电阻,最小-最大生成树,局部推理

英文摘要:

Variational approximation, such as mean-field (MF) and tree-reweighted (TRW), provide a computationally efficient approximation of the log-partition function for a generic graphical model. TRW provably provides an upper bound, but the approximation ratio is generally not quantified. As the primary contribution of this work, we provide an approach to quantify the approximation ratio through the property of the underlying graph structure. Specifically, we argue that (a variant of) TRW produces an estimate that is within factor $\frac{1}{\sqrt{κ(G)}}$ of the true log-partition function for any discrete pairwise graphical model over graph $G$, where $κ(G) \in (0,1]$ captures how far $G$ is from tree structure with $κ(G) = 1$ for trees and $2/N$ for the complete graph over $N$ vertices. As a consequence, the approximation ratio is $1$ for trees, $\sqrt{(d+1)/2}$ for any graph with maximum average degree $d$, and $\stackrel{β\to\infty}{\approx} 1+1/(2β)$ for graphs with girth (shortest cycle) at least $β\log N$. In general, $κ(G)$ is the solution of a max-min problem associated with $G$ that can be evaluated in polynomial time for any graph. Using samples from the uniform distribution over the spanning trees of G, we provide a near linear-time variant that achieves an approximation ratio equal to the inverse of square-root of minimal (across edges) effective resistance of the graph. We connect our results to the graph partition-based approximation method and thus provide a unified perspective. Keywords: variational inference, log-partition function, spanning tree polytope, minimum effective resistance, min-max spanning tree, local inference

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。

↑