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 1410.7659cs.LGcs.ITmath.ITstat.COstat.ML
收藏

从Glauber动力学学习图形模型

Learning graphical models from the Glauber dynamics

Massachusetts Institute of Technology(麻省理工学院)

Guy Bresler, David Gamarnik, Devavrat Shah

摘要:

在本文中,我们考虑的问题,学习无向图形模型的数据生成的根据Glauber动力学。Glauber动力学是一个马尔可夫链,它顺序地更新图形模型中的各个节点(变量),并且经常用于从平稳分布(给定足够的时间,它会收敛到平稳分布)中进行采样。此外,Glauber动力学是各种设置中的自然动力学模型。这项工作偏离了文献中图形模型学习的标准公式,其中假设可以访问i.i.d.。分布的样本。许多关于图形模型学习的研究都是针对寻找低计算成本的算法。作为这项工作的主要结果,我们建立的问题,重建二进制成对图形模型是计算易处理的,当我们观察到的Glauber动力学。具体来说,我们表明,一个二进制成对图形模型$p$节点的最大程度$d$可以学习的时间$f(d)p^2\log p$,为一个功能$f(d)$,使用几乎信息理论的最小样本数。

英文摘要:

In this paper we consider the problem of learning undirected graphical models from data generated according to the Glauber dynamics. The Glauber dynamics is a Markov chain that sequentially updates individual nodes (variables) in a graphical model and it is frequently used to sample from the stationary distribution (to which it converges given sufficient time). Additionally, the Glauber dynamics is a natural dynamical model in a variety of settings. This work deviates from the standard formulation of graphical model learning in the literature, where one assumes access to i.i.d. samples from the distribution. Much of the research on graphical model learning has been directed towards finding algorithms with low computational cost. As the main result of this work, we establish that the problem of reconstructing binary pairwise graphical models is computationally tractable when we observe the Glauber dynamics. Specifically, we show that a binary pairwise graphical model on $p$ nodes with maximum degree $d$ can be learned in time $f(d)p^2\log p$, for a function $f(d)$, using nearly the information-theoretic minimum number of samples.

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。

↑