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 1802.06129cs.LGmath.CO
收藏

自由能的顶点采样复杂度为多项式

The Vertex Sample Complexity of Free Energy is Polynomial

Massachusetts Institute of Technology(麻省理工学院)

Vishesh Jain, Frederic Koehler, Elchanan Mossel

摘要:

我们研究以下问题:给定一个大规模的马尔可夫随机场上的$n$节点,可以从它提供一个粗略的近似自由能$\mathcal{F}_n = \log{Z_n}$的小样本?Borgs、Chayes、Lovász、Sós和Vesztergombi在图极限文献中的结果表明,对于$n$节点上的Ising模型和强度$Θ(1/n)$的相互作用,可以通过在$2^{O(1/ε^2)}$节点上采样随机诱导模型来实现对$\log Z_n / n$的$ε$近似。我们证明了该问题的采样复杂性为{ \em polynomial in} $1/ε$ .我们进一步表明,多项式依赖于$ε$是不可避免的。我们的结果是非常普遍的,因为它们适用于高阶马尔可夫随机场。对于$r$阶的马尔可夫随机场,我们得到了一个算法,该算法利用$r$和$1/ε$中的多项式样本数和运行时间达到$r$和$ε$中多项式因子的$2^{O(1/ε^2)}$,来实现$ε$逼近.对于铁磁Ising模型,在$1/ε$中,运行时间是多项式的.我们的研究结果是密切相关的正则性引理和性能测试,在那里的兴趣是在寻找哪些属性可以测试在$ε$错误的时间多项式在$1/ε$的最近的研究。特别是,我们的证明建立在阿隆,德拉维加,Kannan和Karpinski,谁也介绍了多项式顶点样本复杂性的概念最近的工作的结果。另一个关键成分的证明是一个有效的约束作者的文件有关的变分自由能和自由能。

英文摘要:

We study the following question: given a massive Markov random field on $n$ nodes, can a small sample from it provide a rough approximation to the free energy $\mathcal{F}_n = \log{Z_n}$? Results in graph limit literature by Borgs, Chayes, Lovász, Sós, and Vesztergombi show that for Ising models on $n$ nodes and interactions of strength $Θ(1/n)$, an $ε$ approximation to $\log Z_n / n$ can be achieved by sampling a randomly induced model on $2^{O(1/ε^2)}$ nodes. We show that the sampling complexity of this problem is {\em polynomial in} $1/ε$. We further show a polynomial dependence on $ε$ cannot be avoided. Our results are very general as they apply to higher order Markov random fields. For Markov random fields of order $r$, we obtain an algorithm that achieves $ε$ approximation using a number of samples polynomial in $r$ and $1/ε$ and running time that is $2^{O(1/ε^2)}$ up to polynomial factors in $r$ and $ε$. For ferromagnetic Ising models, the running time is polynomial in $1/ε$. Our results are intimately connected to recent research on the regularity lemma and property testing, where the interest is in finding which properties can tested within $ε$ error in time polynomial in $1/ε$. In particular, our proofs build on results from a recent work by Alon, de la Vega, Kannan and Karpinski, who also introduced the notion of polynomial vertex sample complexity. Another critical ingredient of the proof is an effective bound by the authors of the paper relating the variational free energy and the free energy.

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。

↑