Federated Over-Air Subspace Tracking From Incomplete and Corrupted Data

In this work we study the problem of Subspace Tracking with missing data (ST-miss) and outliers (Robust ST-miss). We propose a novel algorithm, and provide a guarantee for both these problems. Unlike past work on this topic, the current work does not impose the piecewise constant subspace change assumption. Additionally, the proposed algorithm is much simpler (uses fewer parameters) than our previous work. Secondly, we extend our approach and its analysis to provably solving these problems when the data is federated and when the over-air data communication modality is used for information exchange between the K peer nodes and the center. We validate our theoretical claims with extensive numerical experiments.

Automated summary

This work addresses the problem of Subspace Tracking with missing data and outliers. It proposes a novel algorithm that does not assume piecewise constant subspace change and is simpler compared to previous approaches. Furthermore, the study extends its approach to solving these problems in federated settings and over-air data communication mode.