A Combinatorial Algebraic Approach for the Identifiability of Low-Rank Matrix Completion
Franz Kiraly (TU Berlin), Ryota Tomioka (University of Tokyo)

TL;DR
This paper introduces a novel algebraic and combinatorial framework to determine when low-rank matrices can be uniquely reconstructed from partial entries, providing new theoretical insights and practical algorithms that outperform existing methods.
Contribution
It establishes the first necessary and sufficient combinatorial conditions for low-rank matrix identifiability, linking algebraic geometry, combinatorics, and graph theory.
Findings
Derived tight combinatorial conditions for matrix identifiability
Developed algorithms that outperform state-of-the-art methods
Validated conditions and algorithms on practical matrix sizes
Abstract
In this paper, we review the problem of matrix completion and expose its intimate relations with algebraic geometry, combinatorics and graph theory. We present the first necessary and sufficient combinatorial conditions for matrices of arbitrary rank to be identifiable from a set of matrix entries, yielding theoretical constraints and new algorithms for the problem of matrix completion. We conclude by algorithmically evaluating the tightness of the given conditions and algorithms for practically relevant matrix sizes, showing that the algebraic-combinatoric approach can lead to improvements over state-of-the-art matrix completion methods.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Topicsgraph theory and CDMA systems · Sparse and Compressive Sensing Techniques · Matrix Theory and Algorithms
