A Characterization of Deterministic Sampling Patterns for Low-Rank Matrix Completion

Low-rank matrix completion (LRMC) problems arise in a wide variety of applications. Previous theory mainly provides conditions for completion under missing-at-random samplings. This paper studies deterministic conditions for completion. An incomplete d × N matrix is finitely rank-r completable if there are at most finitely many rank-r matrices that agree with all its observed entries. Finite completability is the tipping point in LRMC, as a few additional samples of a finitely completable matrix guarantee its unique completability. The main contribution of this paper is a deterministic sampling condition for finite completability. We use this to also derive deterministic sampling conditions for unique completability that can be efficiently verified. We also show that under uniform random sampling schemes, these conditions are satisfied with high probability if O({r, d}) entries per column are observed. These findings have several implications on LRMC regarding lower bounds, sample and computational complexity, the role of coherence, adaptive settings and the validation of any completion algorithm. We complement our theoretical results with experiments that support our findings and motivate future analysis of uncharted sampling regimes.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/05/2017

On Deterministic Sampling Patterns for Robust Low-Rank Matrix Completion

In this letter, we study the deterministic sampling patterns for the com...
research
10/02/2019

A deterministic theory of low rank matrix completion

The problem of completing a large low rank matrix using a subset of reve...
research
02/03/2023

Support Recovery in Sparse PCA with Non-Random Missing Data

We analyze a practical algorithm for sparse PCA on incomplete and noisy ...
research
03/22/2017

Characterization of Deterministic and Probabilistic Sampling Patterns for Finite Completability of Low Tensor-Train Rank Tensor

In this paper, we analyze the fundamental conditions for low-rank tensor...
research
03/31/2017

Fundamental Conditions for Low-CP-Rank Tensor Completion

We consider the problem of low canonical polyadic (CP) rank tensor compl...
research
04/12/2018

Exact Reconstruction of Euclidean Distance Geometry Problem Using Low-rank Matrix Completion

The Euclidean distance geometry problem arises in a wide variety of appl...
research
11/09/2020

Statistical Query Complexity of Manifold Estimation

This paper studies the statistical query (SQ) complexity of estimating d...

Please sign up or login with your details

Forgot password? Click here to reset