arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.04728cs.DScs.LGstat.ML
收藏

具有独立失效的Ising模型的学习

Learning Ising Models with Independent Failures

University of Texas at Austin(德克萨斯大学奥斯汀分校);UCSD(加州大学圣地亚哥分校)

Surbhi Goel, Daniel M. Kane, Adam R. Klivans

摘要:

我们给出了第一个有效的算法,用于学习容忍独立故障的伊辛模型的结构;也就是说,观察到的样本的每个条目都以某种未知的概率p丢失。我们的算法与Klivans和Meka(2017)最近学习伊辛模型的工作的基本最佳运行时间和样本复杂度界限相匹配。我们为Vuffray等人(2016)的交互筛选目标(ISO)的梯度设计了一种新的无偏估计量,并应用随机乘法梯度下降算法来最小化该目标。这种最小化的解决方案逐个节点恢复底层伊辛模型的邻域信息。

英文摘要:

We give the first efficient algorithm for learning the structure of an Ising model that tolerates independent failures; that is, each entry of the observed sample is missing with some unknown probability p. Our algorithm matches the essentially optimal runtime and sample complexity bounds of recent work for learning Ising models due to Klivans and Meka (2017). We devise a novel unbiased estimator for the gradient of the Interaction Screening Objective (ISO) due to Vuffray et al. (2016) and apply a stochastic multiplicative gradient descent algorithm to minimize this objective. Solutions to this minimization recover the neighborhood information of the underlying Ising model on a node by node basis.

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。

↑