New Riemannian preconditioned algorithms for tensor completion via polyadic decomposition

Abstract

We propose new Riemannian preconditioned algorithms for low-rank tensor completion via the polyadic decomposition of a tensor. These algorithms exploit a non-Euclidean metric on the product space of the factor matrices of the low-rank tensor in the polyadic decomposition form. This new metric is designed using an approximation of the diagonal blocks of the Hessian of the tensor completion cost function, thus has a preconditioning effect on these algorithms. We prove that the proposed Riemannian gradient descent algorithm globally converges to a stationary point of the tensor completion problem, with convergence rate estimates using the $Ł$ojasiewicz property. Numerical results on synthetic and real-world data suggest that the proposed algorithms are more efficient in memory and time compared to state-of-the-art algorithms. Moreover, the proposed algorithms display a greater tolerance for overestimated rank parameters in terms of the tensor recovery performance, thus enable a flexible choice of the rank parameter.

arXiv comment27 Pages, 10 figures, 4 tables

References in corpus (14)

• Tensor Decompositions for Signal Processing Applications From Two-way to Multiway Component Analysis
• Manopt, a Matlab toolbox for optimization on manifolds
• Scalable Tensor Factorizations for Incomplete Data
• Smooth PARAFAC Decomposition for Tensor Completion
• Global rates of convergence for nonconvex optimization on manifolds
• Provable Tensor Factorization with Missing Data
• Low-rank tensor completion: a Riemannian manifold preconditioning approach
• Riemannian preconditioning
• A Riemannian geometry for low-rank matrix completion
• Simple tensor products
• A Riemannian Trust Region Method for the Canonical Tensor Rank Approximation Problem
• Efficient tensor completion: Low-rank tensor train
• Alternating Least Squares Tensor Completion in The TT-Format
• Alternating minimization algorithms for graph regularized tensor completion

Cited by in corpus (2)

• Low-rank Tensor Estimation via Riemannian Gauss-Newton: Statistical Optimality and Second-Order Convergence
• A Riemannian gradient descent method for optimization on the indefinite Stiefel manifold