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 1309.6550cs.ITcond-mat.stat-mechmath.IT
收藏

使用信息几何概念的非二进制字母循环演算

Loop Calculus for Non-Binary Alphabets using Concepts from Information Geometry

Ryuhei Mori

摘要:

贝特近似(英语:Bethe approximation)是统计物理学中常用的配分函数的一种近似。最近,Chertkov和Chernyak给出了二元图形模型的配分函数与Bethe近似之间的一个关系式。在这个等式中,Bethe近似中的乘法误差表示为图形模型中所有广义循环的加权和。本文利用信息几何中的概念,将等式推广到非二进制字母表的图模型。

英文摘要:

The Bethe approximation is a well-known approximation of the partition function used in statistical physics. Recently, an equality relating the partition function and its Bethe approximation was obtained for graphical models with binary variables by Chertkov and Chernyak. In this equality, the multiplicative error in the Bethe approximation is represented as a weighted sum over all generalized loops in the graphical model. In this paper, the equality is generalized to graphical models with non-binary alphabet using concepts from information geometry.

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。

↑