Poster
Non-convex Statistical Optimization for Sparse Tensor Graphical Model
Wei Sun · Zhaoran Wang · Han Liu · Guang Cheng

Wed Dec 9th 07:00 -- 11:59 PM @ 210 C #79 #None
in Poster Session »

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.

Author Information

Will Wei Sun (Yahoo Labs)
Zhaoran Wang (Princeton University)
Han Liu (Princeton University)
Guang Cheng (Purdue University)

More from the Same Authors