Tensor Completion by Alternating Minimization under the Tensor Train (TT) Model

Abstract

Using the matrix product state (MPS) representation of tensor train decompositions, in this paper we propose a tensor completion algorithm which alternates over the matrices (tensors) in the MPS representation. This development is motivated in part by the success of matrix completion algorithms which alternate over the (low-rank) factors. We comment on the computational complexity of the proposed algorithm and numerically compare it with existing methods employing low rank tensor train approximation for data completion as well as several other recently proposed methods. We show that our method is superior to existing ones for a variety of real settings.

References in corpus (1)

• Efficient tensor completion: Low-rank tensor train

Cited by in corpus (15)

• Provable Tensor Ring Completion
• Tensor Train Neighborhood Preserving Embedding
• Wide Compression: Tensor Ring Nets
• On Tensor Train Rank Minimization: Statistical Efficiency and Scalable Algorithm
• Quantum State Tomography for Matrix Product Density Operators
• Provable Tensor-Train Format Tensor Completion by Riemannian Optimization
• High-dimension Tensor Completion via Gradient-based Optimization Under Tensor-train Format
• Low-rank Tensor Grid for Image Completion
• Deterministic and Probabilistic Conditions for Finite Completability of Low-rank Multi-View Data
• Principal Component Analysis with Tensor Train Subspace
• Lower and Upper Bounds on the VC-Dimension of Tensor Network Models
• Deterministic and Probabilistic Conditions for Finite Completability of Low-Tucker-Rank Tensor
• Implicit Regularization and Entrywise Convergence of Riemannian Optimization for Low Tucker-Rank Tensor Completion
• TenIPS: Inverse Propensity Sampling for Tensor Completion
• Tensor-Train Parameterization for Ultra Dimensionality Reduction