Noisy Tensor Completion for Tensors with a Sparse Canonical Polyadic Factor

2017/04/08 by Jain, Swayambhoo, Gutierrez, Alexander, Haupt, Jarvis
#FOS: Computer and information sciences #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1704.02534

Abstract

In this paper we study the problem of noisy tensor completion for tensors that admit a canonical polyadic or CANDECOMP/PARAFAC (CP) decomposition with one of the factors being sparse. We present general theoretical error bounds for an estimate obtained by using a complexity-regularized maximum likelihood principle and then instantiate these bounds for the case of additive white Gaussian noise. We also provide an ADMM-type algorithm for solving the complexity-regularized maximum likelihood problem and validate the theoretical finding via experiments on synthetic data set.

Related

• Sparse Nonnegative Tensor Factorization and Completion with Noisy Observations
• The Average Spectrum Norm and Near-Optimal Tensor Completion
• Revisit CP Tensor Decomposition: Statistical Optimality and Fast Convergence
• Fundamental Conditions for Low-CP-Rank Tensor Completion
• Exact Tensor Completion from Sparsely Corrupted Observations via Convex Optimization