Matrix Completion With Deterministic Pattern: A Geometric Perspective

DOI10.1109/TSP.2018.2885494zbMATH Open1414.15034arXiv1802.00047WikidataQ128771885 ScholiaQ128771885MaRDI QIDQ4628264FDOQ4628264

Authors: Alexander Shapiro, Yao Xie, Rui Zhang 

Publication date: 6 March 2019

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Abstract: We consider the matrix completion problem with a deterministic pattern of observed entries. In this setting, we aim to answer the question: under what condition there will be (at least locally) unique solution to the matrix completion problem, i.e., the underlying true matrix is identifiable. We answer the question from a certain point of view and outline a geometric perspective. We give an algebraically verifiable sufficient condition, which we call the well-posedness condition, for the local uniqueness of MRMC solutions. We argue that this condition is necessary for local stability of MRMC solutions, and we show that the condition is generic using the characteristic rank. We also argue that the low-rank approximation approaches are more stable than MRMC and further propose a sequential statistical testing procedure to determine the "true" rank from observed entries. Finally, we provide numerical examples aimed at verifying validity of the presented theory.

Full work available at URL: https://arxiv.org/abs/1802.00047

Mathematics Subject Classification ID

Approximation methods and heuristics in mathematical programming (90C59) Matrix completion problems (15A83) Nonconvex programming, global optimization (90C26)

Cited In (3)

• Noisy matrix completion: understanding statistical guarantees for convex relaxation via nonconvex optimization
• Matrix completion with nonconvex regularization: spectral operators and scalable algorithms
• Bayesian uncertainty quantification for low-rank matrix completion

This page was built for publication: Matrix Completion With Deterministic Pattern: A Geometric Perspective

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4628264)