TU4.R7.3

Fusion over the Grassmannian for High-Rank Matrix Completion

Jeremy Johnson, Huanran Li, Daniel Pimentel-Alarcon, University of Wisconsin - Madison, United States

Session:
Rank Metric Codes

Track:
1: Algebraic Aspects of Coding Theory

Location:
VIP

Presentation Time:
Tue, 9 Jul, 16:45 - 17:05

Session Chair:
Ferdinando Zullo, Universita della Campania
Abstract
This paper presents a new paradigm to cluster and complete data lying in a union of subspaces using points on the Grassmannian as proxies. Our approach does not require prior knowledge of the number of subspaces, is naturally suited to handle noise, and only requires an upper bound on the subspaces' dimensions. We detail clustering, completion, model section, and sketching techniques that can be used in practice. We complement our discussion with synthetic and real-data experiments, which show that our approach performs comparable to the state-of-the art in the {\em easy} cases (high sampling rates), and significantly better in the {\em difficult} cases (low sampling rates), thus shortening the gap towards the fundamental sampling limit of HRMC.
Resources