arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.09370math.STcs.LGstat.TH
收藏

从一个或多个样本中学习Ising模型

Learning Ising models from one or multiple samples

MIT(麻省理工学院);Google Research(谷歌研究院)

Yuval Dagan, Constantinos Daskalakis, Nishanth Dikkala, Anthimos Vardis Kandiros

摘要:

估计伊辛模型有两条独立的工作路线:(1)在对模型交互矩阵的最小假设下,从多个独立样本中估计它们;(2)在限制性设置中从一个样本中估计它们。我们提出了一个统一的框架,平滑地在这两个设置之间插值,从而从一个,几个或多个样本中获得更丰富的估计保证。我们的主要定理提供了保证单样本估计,量化的相互作用矩阵的家庭的度量熵方面的估计误差。作为我们的主要定理的推论,我们推导出边界时,模型的相互作用矩阵是一个(稀疏)线性组合的已知矩阵,或者它属于一个有限集,或一个高维流形。事实上,我们的主要结果处理多个独立的样本,通过查看它们作为一个样本从一个更大的模型,并可以用来推导出估计界限,定性类似于在上述多样本文献中获得的。我们的技术方法受益于稀疏化模型的交互网络,对变量子集进行调节,使所得到的条件分布中的依赖性足够弱。我们使用这种稀疏化技术来证明伊辛模型的强浓度和反浓度的结果,我们相信有超出本文范围的应用。

英文摘要:

There have been two separate lines of work on estimating Ising models: (1) estimating them from multiple independent samples under minimal assumptions about the model's interaction matrix; and (2) estimating them from one sample in restrictive settings. We propose a unified framework that smoothly interpolates between these two settings, enabling significantly richer estimation guarantees from one, a few, or many samples. Our main theorem provides guarantees for one-sample estimation, quantifying the estimation error in terms of the metric entropy of a family of interaction matrices. As corollaries of our main theorem, we derive bounds when the model's interaction matrix is a (sparse) linear combination of known matrices, or it belongs to a finite set, or to a high-dimensional manifold. In fact, our main result handles multiple independent samples by viewing them as one sample from a larger model, and can be used to derive estimation bounds that are qualitatively similar to those obtained in the afore-described multiple-sample literature. Our technical approach benefits from sparsifying a model's interaction network, conditioning on subsets of variables that make the dependencies in the resulting conditional distribution sufficiently weak. We use this sparsification technique to prove strong concentration and anti-concentration results for the Ising model, which we believe have applications beyond the scope of this paper.

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。

↑