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 2104.00995cs.LGcond-mat.stat-mechphysics.data-anstat.ML
收藏

基于Ising模型动力学学习的样本复杂度指数降低

Exponential Reduction in Sample Complexity with Learning of Ising Model Dynamics

Massachusetts Institute of Technology(麻省理工学院);Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室)

Arkopal Dutt, Andrey Y. Lokhov, Marc Vuffray, Sidhant Misra

摘要:

用于学习图形模型的结构和参数的通常设置假设从相应的多元概率分布产生的独立样本的可用性。然而,对于许多模型,各个马尔可夫链的混合时间可以非常大,并且独立同分布。可能无法获得样品。我们研究的问题,重建二进制图形模型的相关样本产生的动态过程,这是自然的,在许多应用中。我们分析了两个估计的样本复杂性,这是基于相互作用的筛选目标和条件似然损失。我们观察到,对于来自远离平衡的动态过程的样本,与快速混合的动态过程相比,样本复杂性呈指数级降低。

英文摘要:

The usual setting for learning the structure and parameters of a graphical model assumes the availability of independent samples produced from the corresponding multivariate probability distribution. However, for many models the mixing time of the respective Markov chain can be very large and i.i.d. samples may not be obtained. We study the problem of reconstructing binary graphical models from correlated samples produced by a dynamical process, which is natural in many applications. We analyze the sample complexity of two estimators that are based on the interaction screening objective and the conditional likelihood loss. We observe that for samples coming from a dynamical process far from equilibrium, the sample complexity reduces exponentially compared to a dynamical process that mixes quickly.

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。

↑