Deterministic and Probabilistic Conditions for Finite Completability of Low-rank Multi-View Data

TL;DR

This paper establishes deterministic and probabilistic conditions on sampling patterns that ensure the finite and unique completion of multi-view low-rank data matrices, extending matrix completion theory to multi-view scenarios.

Contribution

It introduces a geometric manifold-based analysis for multi-view data completion, providing new deterministic and probabilistic guarantees for finite and unique completability.

Findings

Deterministic necessary and sufficient conditions for finite completability.

Probabilistic guarantees based on sample size per column.

Extension of matrix completion theory to multi-view data.

Abstract

We consider the multi-view data completion problem, i.e., to complete a matrix $\mathbf{U}=[\mathbf{U}_1|\mathbf{U}_2]$ where the ranks of $\mathbf{U},\mathbf{U}_1$, and $\mathbf{U}_2$ are given. In particular, we investigate the fundamental conditions on the sampling pattern, i.e., locations of the sampled entries for finite completability of such a multi-view data given the corresponding rank constraints. In contrast with the existing analysis on Grassmannian manifold for a single-view matrix, i.e., conventional matrix completion, we propose a geometric analysis on the manifold structure for multi-view data to incorporate more than one rank constraint. We provide a deterministic necessary and sufficient condition on the sampling pattern for finite completability. We also give a probabilistic condition in terms of the number of samples per column that guarantees finite completability with high probability. Finally, using the developed tools, we derive the deterministic and probabilistic guarantees for unique completability.