A Riemannian trust-region method for low-rank tensor completion

Abstract

The goal of tensor completion is to fill in missing entries of a partially known tensor (possibly including some noise) under a low-rank constraint. This may be formulated as a least-squares problem. The set of tensors of a given multilinear rank is known to admit a Riemannian manifold structure, thus methods of Riemannian optimization are applicable. In our work, we derive the Riemannian Hessian of an objective function on the low-rank tensor manifolds using the Weingarten map, a concept from differential geometry. We discuss the convergence properties of Riemannian trust-region methods based on the exact Hessian and standard approximations, both theoretically and numerically. We compare our approach to Riemannian tensor completion methods from recent literature, both in terms of convergence behaviour and computational complexity. Our examples include the completion of randomly generated data with and without noise and recovery of multilinear data from survey statistics.

Cited by in corpus (7)

• The condition number of Riemannian approximation problems
• Stability analysis of hierarchical tensor methods for time-dependent PDEs
• Low-rank Tensor Estimation via Riemannian Gauss-Newton: Statistical Optimality and Second-Order Convergence
• A Riemannian Newton Trust-Region Method for Fitting Gaussian Mixture Models
• Global Riemannian Acceleration in Hyperbolic and Spherical Spaces
• Implicit Regularization and Entrywise Convergence of Riemannian Optimization for Low Tucker-Rank Tensor Completion
• Riemannian Conjugate Gradient Descent Method for Third-Order Tensor Completion