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 2201.10548math.STcs.AIcs.LGstat.MLstat.TH
收藏

高斯DAG模型的最优估计

Optimal estimation of Gaussian DAG models

University of Chicago(芝加哥大学)

Ming Gao, Wai Ming Tai, Bryon Aragam

摘要:

研究了从观测数据中学习高斯有向无圈图(DAG)的最优样本复杂度。我们的主要结果建立了极小极大最优样本复杂性学习的线性高斯DAG模型的结构在两个设置的兴趣:1)在等方差下,没有知识的真实顺序,和2)对于一般的线性模型给定的知识的顺序。在这两种情况下,样本复杂度都是$n\asymp q\log(d/q)$,其中$q$是父节点的最大数量,$d$是节点的数量。我们进一步与学习(无向)高斯图模型的经典问题进行比较,表明在等方差假设下,这两个问题具有相同的最优样本复杂度。换句话说,至少对于具有相等误差方差的高斯模型,学习有向图模型在统计上并不比学习无向图模型更困难。我们的研究结果也扩展到更一般的识别假设以及亚高斯误差。

英文摘要:

We study the optimal sample complexity of learning a Gaussian directed acyclic graph (DAG) from observational data. Our main results establish the minimax optimal sample complexity for learning the structure of a linear Gaussian DAG model in two settings of interest: 1) Under equal variances without knowledge of the true ordering, and 2) For general linear models given knowledge of the ordering. In both cases the sample complexity is $n\asymp q\log(d/q)$, where $q$ is the maximum number of parents and $d$ is the number of nodes. We further make comparisons with the classical problem of learning (undirected) Gaussian graphical models, showing that under the equal variance assumption, these two problems share the same optimal sample complexity. In other words, at least for Gaussian models with equal error variances, learning a directed graphical model is statistically no more difficult than learning an undirected graphical model. Our results also extend to more general identification assumptions as well as subgaussian errors.

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。

↑