MLApr 8, 2017

Noisy Tensor Completion for Tensors with a Sparse Canonical Polyadic Factor

arXiv:1704.02534v14 citations
Originality Incremental advance
AI Analysis

This work addresses tensor completion for a specific structural case, which is incremental as it builds on existing CP decomposition methods by incorporating sparsity constraints.

The paper tackles noisy tensor completion for tensors with a sparse CP factor, deriving theoretical error bounds for an estimate using complexity-regularized maximum likelihood and validating them with experiments on synthetic data.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes