Parallel matrix factorization for low-rank tensor completion

Abstract

Higher-order low-rank tensors naturally arise in many applications including hyperspectral data recovery, video inpainting, seismic data recon- struction, and so on. We propose a new model to recover a low-rank tensor by simultaneously performing low-rank matrix factorizations to the all-mode ma- tricizations of the underlying tensor. An alternating minimization algorithm is applied to solve the model, along with two adaptive rank-adjusting strategies when the exact rank is not known. Phase transition plots reveal that our algorithm can recover a variety of synthetic low-rank tensors from significantly fewer samples than the compared methods, which include a matrix completion method applied to tensor recovery and two state-of-the-art tensor completion methods. Further tests on real- world data show similar advantages. Although our model is non-convex, our algorithm performs consistently throughout the tests and give better results than the compared methods, some of which are based on convex models. In addition, the global convergence of our algorithm can be established in the sense that the gradient of Lagrangian function converges to zero.

25 pages, 12 figures

References in corpus (4)

• Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery
• A New Convex Relaxation for Tensor Completion
• A globally convergent algorithm for nonconvex optimization based on block coordinate update
• Novel Factorization Strategies for Higher Order Tensors: Implications for Compression and Recovery of Multi-linear Data

Cited by in corpus (45)

• Efficient tensor completion for color image and video recovery: Low-rank tensor train
• Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery
• Framelet Representation of Tensor Nuclear Norm for Third-Order Tensor Completion
• Guaranteed Tensor Recovery Fused Low-rankness and Smoothness
• Multi-dimensional imaging data recovery via minimizing the partial sum of tubal nuclear norm
• Brain-Computer Interface with Corrupted EEG Data: A Tensor Completion Approach
• Efficient tensor completion: Low-rank tensor train
• Inexact Alternating Optimization for Phase Retrieval In the Presence of Outliers
• Tensor Completion Algorithms in Big Data Analytics
• Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration
• Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion
• Tensor factorization based method for low rank matrix completion and its application on tensor completion
• Manifold Modeling in Embedded Space: A Perspective for Interpreting Deep Image Prior
• Robust Tensor Completion Using Transformed Tensor SVD
• Multi-Tubal Rank of Third Order Tensor and Related Low Rank Tensor Completion Problem
• Low-rank Tensor Grid for Image Completion
• Beyond Low Rank: A Data-Adaptive Tensor Completion Method
• Fast and Accurate Tensor Completion with Total Variation Regularized Tensor Trains
• Taming Convergence for Asynchronous Stochastic Gradient Descent with Unbounded Delay in Non-Convex Learning
• Higher order Matching Pursuit for Low Rank Tensor Learning
• Regularized and Smooth Double Core Tensor Factorization for Heterogeneous Data
• Fast algorithms for Higher-order Singular Value Decomposition from incomplete data
• Accelerated and Inexact Soft-Impute for Large-Scale Matrix and Tensor Completion
• T product Tensors Part I: Inequalities
• Concatenated image completion via tensor augmentation and completion
• Hierarchical Tensor Ring Completion
• Robust Low-tubal-rank Tensor Completion based on Tensor Factorization and Maximum Correntopy Criterion
• Implicit Regularization and Entrywise Convergence of Riemannian Optimization for Low Tucker-Rank Tensor Completion
• FasTer: Fast Tensor Completion with Nonconvex Regularization
• Enhanced nonconvex low-rank approximation of tensor multi-modes for tensor completion
• Low-Rank and Sparse Enhanced Tucker Decomposition for Tensor Completion
• Multi-mode Core Tensor Factorization based Low-Rankness and Its Applications to Tensor Completion
• Tensor Completion via Tensor Networks with a Tucker Wrapper
• On the tensor nuclear norm and the total variation regularization for image and video completion
• Tensor Q-Rank: New Data Dependent Definition of Tensor Rank
• Generalized T-product Tensor Bernstein Bounds
• Quaternion tensor low rank Quaternion tensor low-rank approximation using a family of non-convex norms
• Tensor Completion through Total Variationwith Initialization from Weighted HOSVD
• An Efficient Tensor Completion Method via New Latent Nuclear Norm
• Noisy Tensor Completion for Tensors with a Sparse Canonical Polyadic Factor
• T-product Tensor Expander Chernoff Bound
• Low-rank quaternion tensor completion for recovering color videos and images
• Multi-tensor Completion for Estimating Missing Values in Video Data
• Nonnegative Low Rank Tensor Approximation and its Application to Multi-dimensional Images
• Tensor Completion via Convolutional Sparse Coding Regularization