arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.00441math.STstat.TH
收藏

有限样本收敛速率的Bigraphical和Tensor graphical Lasso估计量

Finite sample rates of convergence for the Bigraphical and Tensor graphical Lasso estimators

University of California, Riverside(加州大学河滨分校);MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室)

Shuheng Zhou, Kristjan Greenewald

AI总结:

本文改进了Bigraphical和TeraLasso估计量的收敛速率,解决了两种方式模型中有限样本误差的理论保证问题。

摘要:

许多现代数据集表现出观测值之间的依赖关系以及变量之间的依赖关系。十年前,Kalaitzis等人(2013)提出了Bigraphical Lasso,这是一种基于图的笛卡尔积的估计量,用于估计矩阵正态分布的精度矩阵;他们观察到Kronecker和的结合性导致了一种对组织成3阶或更高阶张量的数据集建模的方法。随后,Greenewald、Zhou和Hero(2019)深入探讨了这一可能性,通过引入张量图Lasso(TeraLasso)来估计所有L≥2的稀疏L-way可分解逆协方差矩阵,并展示了在Frobenius范数和算子范数下估计此类逆协方差矩阵的收敛速率。在本文中,我们为Bigraphical和TeraLasso估计量提供了更精确的收敛速率,这优于GZH 2019中提出的速率。特别是,(a)我们通过约log p的因子加强了算子范数和Frobenius范数下的相对误差界;(b)关键的是,这种改进使得在两种方式Kronecker和模型中可以推导出两种范数下的有限样本估计误差。这填补了在两种方式模型中观察到的低单样本误差与该特定情况缺乏理论保证之间的差距。两种方式的设定很重要,因为它是最具理论挑战性的设定,同时也是应用中最常见的设定。在本文中,我们详细阐述了Kronecker和模型,突出了证明策略,并提供了所有主要定理的完整证明。

英文摘要:

Many modern datasets exhibit dependencies among observations as well as variables. A decade ago, Kalaitzis et. al. (2013) proposed the Bigraphical Lasso, an estimator for precision matrices of matrix-normals based on the Cartesian product of graphs; they observed that the associativity of the Kronecker sum yields an approach to the modeling of datasets organized into 3 or higher-order tensors. Subsequently, Greenewald, Zhou and Hero (2019) explored this possibility to a great extent, by introducing the tensor graphical Lasso (TeraLasso) for estimating sparse $L$-way decomposable inverse covariance matrices for all $L \ge 2$, and showing the rates of convergence in the Frobenius and operator norms for estimating this class of inverse covariance matrices for sub-gaussian tensor-valued data. In this paper, we provide sharper rates of convergence for both Bigraphical and TeraLasso estimators for inverse covariance matrices. This improves upon the rates presented in GZH 2019. In particular, (a) we strengthen the bounds for the relative errors in the operator and Frobenius norm by a factor of approximately $\log p$; (b) Crucially, this improvement allows for finite sample estimation errors in both norms to be derived for the two-way Kronecker sum model. This closes the gap between the low single-sample error for the two-way model as observed in GZH 2019 and the lack of theoretical guarantee for this particular case. The two-way regime is important because it is the setting that is the most theoretically challenging, and simultaneously the most common in applications. In the current paper, we elaborate on the Kronecker Sum model, highlight the proof strategy and provide full proofs of all main theorems.

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。

↑