Information Geometry of Reversible Markov Chains

Information Geometry of Reversible Markov Chains
复制标题

可逆马尔可夫链的信息几何

DOI:
10.1007/s41884-021-00061-7
复制
发表时间:
2021
期刊:
Information Geometry
影响因子:
--
通讯作者:
Watanabe Shun
Watanabe Shun
中科院分区:
--
文献类型:
--
作者:
Wolfer Geoffrey;Watanabe Shun

文献摘要

参考文献

被引文献

相似文献

分析了马氏链不可约转移核参数族时间可逆性的信息几何结构。我们定义和表征可逆指数家庭的马尔可夫内核,并表明,不可约和可逆的马尔可夫内核形成一个混合物家庭,也许令人惊讶的是,一个指数家庭的所有随机内核。我们提出了一个参数化的可逆内核的整个流形,并检查可逆测地线。我们定义了信息投影到可逆流形上,并推导出e-投影和m-投影的封闭表达式,沿着与信息发散有关的勾股恒等式,从而引出了马尔可夫核可逆化的一些新概念.我们表明家庭的边缘措施有关的不可约和可逆的内核也形成一个指数家庭之间的分布对。我们进一步探讨了可逆家庭的几何性质,通过比较他们与其他显着的随机矩阵家庭。最后,我们表明,可逆内核,在某种意义上说,我们定义,最小的指数家庭所产生的m-家庭的对称内核,和最小的混合家庭,包括e-家庭的无记忆内核。
We analyze the information geometric structure of time reversibility for parametric families of irreducible transition kernels of Markov chains. We define and characterize reversible exponential families of Markov kernels, and show that irreducible and reversible Markov kernels form both a mixture family and, perhaps surprisingly, an exponential family in the set of all stochastic kernels. We propose a parametrization of the entire manifold of reversible kernels, and inspect reversible geodesics. We define information projections onto the reversible manifold, and derive closed-form expressions for the e-projection and m-projection, along with Pythagorean identities with respect to information divergence, leading to some new notion of reversiblization of Markov kernels. We show the family of edge measures pertaining to irreducible and reversible kernels also forms an exponential family among distributions over pairs. We further explore geometric properties of the reversible family, by comparing them with other remarkable families of stochastic matrices. Finally, we show that reversible kernels are, in a sense we define, the minimal exponential family generated by the m-family of symmetric kernels, and the smallest mixture family that comprises the e-family of memoryless kernels.
Konrad-zuse-zentrum F ¡ Ur Informationstechnik Berlin 计算最近的可逆马尔可夫链 计算最近的可逆马尔可夫链
DOI: --
发表时间: --
期刊:
影响因子: --
作者:
Adam Nielsen;Marcus Weber
通讯作者: Marcus Weber
马尔可夫源的 Jeffreys 混合物的性质
DOI: --
发表时间: --
期刊: IEEE Transactions on Information Theory, accepted for publication
影响因子: --
作者:
J-I. Takeuchi;A. Barron;T. Kawabata
通讯作者: T. Kawabata
DOI: --
发表时间: 2005
期刊: 第28回情報理論とその応用シンポジウム予稿集
影响因子: --
作者:
Doi;T.;Fujito;T.;H.Ishihara;H.Nagaoka
通讯作者: H.Nagaoka
贝叶斯混合的渐近最小最大遗憾
DOI: 10.1109/isit.1998.708923
发表时间: 1998
期刊: Proceedings. 1998 IEEE International Symposium on Information Theory (Cat. No.98CH36252)
影响因子: --
作者:
Jun'ichi Takeuchi;Andrew R. Barron
通讯作者: Andrew R. Barron
由上下文树定义的马尔可夫核族的信息几何
DOI: 10.1109/itw.2017.8278008
发表时间: 2017
期刊: 2017 IEEE Information Theory Workshop (ITW)
影响因子: --
作者:
J. Takeuchi;H. Nagaoka
通讯作者: H. Nagaoka