Partial Matrix Completion

TL;DR

This paper introduces a new framework for partial matrix completion that focuses on accurately recovering a large, high-confidence subset of entries, with theoretical guarantees and an online learning extension.

Contribution

It proposes a novel partial matrix completion framework with provable guarantees and an efficient algorithm, including an online variant with low regret.

Findings

High accuracy over completed entries

High coverage of the underlying distribution

Effective online learning algorithm

Abstract

The matrix completion problem aims to reconstruct a low-rank matrix based on a revealed set of possibly noisy entries. Prior works consider completing the entire matrix with generalization error guarantees. However, the completion accuracy can be drastically different over different entries. This work establishes a new framework of partial matrix completion, where the goal is to identify a large subset of the entries that can be completed with high confidence. We propose an efficient algorithm with the following provable guarantees. Given access to samples from an unknown and arbitrary distribution, it guarantees: (a) high accuracy over completed entries, and (b) high coverage of the underlying distribution. We also consider an online learning variant of this problem, where we propose a low-regret algorithm based on iterative gradient updates. Preliminary empirical evaluations are included.