A note on time-uniform concentration inequality for matrix products
Tuan Pham, Alessandro Rinaldo

TL;DR
This paper presents a straightforward method to extend fixed-time concentration bounds to any-time bounds for matrix products, motivated by applications in analyzing Oja's algorithms.
Contribution
It introduces a simple argument that enables time-uniform concentration inequalities for matrix products, enhancing analysis tools for algorithms like Oja's.
Findings
Provides a simple approach for time-uniform concentration bounds.
Applicable to the analysis of Oja's algorithms.
Enables bounds valid at any time, not just fixed points.
Abstract
This short note contains a simple argument that allows us to go from fixed-time to any-time bounds for the concentration of matrix products. The result presented here is motivated by the analysis of Oja's algorithms.
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
TopicsAdvanced Optimization Algorithms Research · Random Matrices and Applications · Stochastic Gradient Optimization Techniques
