Skip to main content

Non-convex statistical optimization for sparse tensor graphical model

Author(s): Sun, W; Wang, Z; Liu, Han; Cheng, G

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1322b
Abstract: We consider the estimation of sparse graphical models that characterize the dependency structure of high-dimensional tensor-valued data. To facilitate the estimation of the precision matrix corresponding to each way of the tensor, we assume the data follow a tensor normal distribution whose covariance has a Kronecker product structure. The penalized maximum likelihood estimation of this model involves minimizing a non-convex objective function. In spite of the non-convexity of this estimation problem, we prove that an alternating minimization algorithm, which iteratively estimates each sparse precision matrix while fixing the others, attains an estimator with the optimal statistical rate of convergence as well as consistent graph recovery. Notably, such an estimator achieves estimation consistency with only one tensor sample, which is unobserved in previous work. Our theoretical results are backed by thorough numerical studies.
Publication Date: 2015
Citation: Sun, Wei, Zhaoran Wang, Han Liu, and Guang Cheng. "Non-convex statistical optimization for sparse tensor graphical model." In Advances in Neural Information Processing Systems 28, (2015): pp. 1081-1089.
ISSN: 1049-5258
Pages: 1081 - 1089
Type of Material: Conference Article
Journal/Proceeding Title: Advances in Neural Information Processing Systems
Version: Author's manuscript



Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.