Regularized Kaczmarz Algorithms for Tensor Recovery

Abstract

Tensor recovery has recently arisen in a lot of application fields, such as transportation, medical imaging and remote sensing. Under the assumption that signals possess sparse and/or low-rank structures, many tensor recovery methods have been developed to apply various regularization techniques together with the operator-splitting type of algorithms. Due to the unprecedented growth of data, it becomes increasingly desirable to use streamlined algorithms to achieve real-time computation, such as stochastic optimization algorithms that have recently emerged as an efficient family of methods in machine learning. In this work, we propose a novel algorithmic framework based on the Kaczmarz algorithm for tensor recovery. We provide thorough convergence analysis and its applications from the vector case to the tensor one. Numerical results on a variety of tensor recovery applications, including sparse signal recovery, low-rank tensor recovery, image inpainting and deconvolution, illustrate the enormous potential of the proposed methods.

References in corpus (9)

• Tensor Regression with Applications in Neuroimaging Data Analysis
• A Gradient Descent Algorithm on the Grassman Manifold for Matrix Completion
• Tensor-based formulation and nuclear norm regularization for multi-energy computed tomography
• Paved with Good Intentions: Analysis of a Randomized Block Kaczmarz Method
• Augmented L1 and Nuclear-Norm Models with a Globally Linearly Convergent Algorithm
• An Asynchronous Parallel Randomized Kaczmarz Algorithm
• On the Randomized Kaczmarz Algorithm
• Convergence of the randomized Kaczmarz method for phase retrieval
• Randomized Kaczmarz for Tensor Linear Systems