Federated Over-Air Subspace Tracking from Incomplete and Corrupted Data
arXiv:2002.12873 · doi:10.1109/TSP.2022.3186540
Abstract
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 peer nodes and the center. We validate our theoretical claims with extensive numerical experiments.
To appear in IEEE Transactions on Signal Processing. changes to writing; more general result provided from which previous result follows as special case
References in corpus (11)
- Federated Learning: Challenges, Methods, and Future Directions
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence
- Towards Federated Learning at Scale: System Design
- Federated Machine Learning: Concept and Applications
- Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
- Non-convex Robust PCA
- Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation
- Federated Principal Component Analysis
- Provable Subspace Tracking from Missing Data and Matrix Completion
- Subspace Estimation from Incomplete Observations: A High-Dimensional Analysis
- Fast Robust Subspace Tracking via PCA in Sparse Data-Dependent Noise