A distributed proximal gradient descent method for tensor completion

2017 ◽  
Author(s):  
T. Papastergiou ◽  
V. Megalooikonomou
Keyword(s):  
Gradient Descent ◽  
Descent Method ◽  
Gradient Descent Method ◽  
Tensor Completion ◽  
Proximal Gradient Descent

scholarly journals Nonparametric Tensor Completion Based on Gradient Descent and Nonconvex Penalty

Symmetry ◽  
2019 ◽  
Vol 11 (12) ◽  
pp. 1512
Author(s):  
Kai Xu ◽  
Zhi Xiong
Keyword(s):  
Gradient Descent ◽  
Image Inpainting ◽  
Descent Method ◽  
Singular Value ◽  
Low Rank ◽  
Iteration Step ◽  
Gradient Descent Method ◽  
Tensor Completion ◽  
Step Size ◽  
Nonconvex Penalty

Existing tensor completion methods all require some hyperparameters. However, these hyperparameters determine the performance of each method, and it is difficult to tune them. In this paper, we propose a novel nonparametric tensor completion method, which formulates tensor completion as an unconstrained optimization problem and designs an efficient iterative method to solve it. In each iteration, we not only calculate the missing entries by the aid of data correlation, but consider the low-rank of tensor and the convergence speed of iteration. Our iteration is based on the gradient descent method, and approximates the gradient descent direction with tensor matricization and singular value decomposition. Considering the symmetry of every dimension of a tensor, the optimal unfolding direction in each iteration may be different. So we select the optimal unfolding direction by scaled latent nuclear norm in each iteration. Moreover, we design formula for the iteration step-size based on the nonconvex penalty. During the iterative process, we store the tensor in sparsity and adopt the power method to compute the maximum singular value quickly. The experiments of image inpainting and link prediction show that our method is competitive with six state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document