A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm
Chi Jin, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, Michael I., Jordan
TL;DR
This paper derives tight concentration inequalities for random vectors with subGaussian norms, extending existing results to a broader class of vectors and providing bounds that are nearly optimal up to logarithmic factors.
Contribution
It introduces new concentration inequalities for subGaussian norm random vectors, generalizing previous bounds and achieving tightness up to logarithmic factors.
Findings
Derived new concentration inequalities for subGaussian norm vectors
Extended bounds to a broader class of random vectors
Achieved near-optimal tightness up to logarithmic factors
Abstract
In this note, we derive concentration inequalities for random vectors with subGaussian norm (a generalization of both subGaussian random vectors and norm bounded random vectors), which are tight up to logarithmic factors.
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
TopicsPoint processes and geometric inequalities · Random Matrices and Applications · Mathematical Approximation and Integration