Efficient Federated Low Rank Matrix Recovery via Alternating GD and Minimization: A Simple Proof
Namrata Vaswani

TL;DR
This paper offers a simplified proof and improved guarantees for the sample complexity of the AltGDmin algorithm in low rank matrix recovery, enhancing understanding and efficiency of federated sensing methods.
Contribution
It presents a significantly simpler proof and an improved sample complexity guarantee for the AltGDmin algorithm in low rank matrix recovery.
Findings
Simplified proof of sample complexity guarantee
Improved theoretical guarantee for AltGDmin
Enhanced understanding of federated low rank matrix recovery
Abstract
This note provides a significantly simpler and shorter proof of our sample complexity guarantee for solving the low rank column-wise sensing problem using the Alternating Gradient Descent (GD) and Minimization (AltGDmin) algorithm. AltGDmin was developed and analyzed for solving this problem in our recent work. We also provide an improved guarantee.
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
TopicsSparse and Compressive Sensing Techniques · Blind Source Separation Techniques · Mathematical Analysis and Transform Methods
