Riemannian Conjugate Gradient Descent Method for Third-Order Tensor Completion

Abstract

The goal of tensor completion is to fill in missing entries of a partially known tensor under a low-rank constraint. In this paper, we mainly study low rank third-order tensor completion problems by using Riemannian optimization methods on the smooth manifold. Here the tensor rank is defined to be a set of matrix ranks where the matrices are the slices of the transformed tensor obtained by applying the Fourier-related transformation onto the tubes of the original tensor. We show that with suitable incoherence conditions on the underlying low rank tensor, the proposed Riemannian optimization method is guaranteed to converge and find such low rank tensor with a high probability. In addition, numbers of sample entries required for solving low rank tensor completion problem under different initialized methods are studied and derived. Numerical examples for both synthetic and image data sets are reported to demonstrate the proposed method is able to recover low rank tensors.

arXiv commentarXiv admin note: substantial text overlap with arXiv:1603.06610 by other authors

References in corpus (10)

• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• A Simpler Approach to Matrix Completion
• Provable Tensor Factorization with Missing Data
• Low-rank tensor completion: a Riemannian manifold preconditioning approach
• A Riemannian trust-region method for low-rank tensor completion
• Efficient tensor completion: Low-rank tensor train
• Guarantees of Riemannian Optimization for Low Rank Matrix Completion
• A dual framework for low-rank tensor completion
• Low-rank matrix completion by Riemannian optimization---extended version
• Exact Tensor Completion from Sparsely Corrupted Observations via Convex Optimization