On the Missing Factor in Some Concentration Inequalities for Martingales
Arun Kumar Kuchibhotla

TL;DR
This paper improves concentration inequalities for martingales with bounded increments, recovering a missing factor in Freedman-style bounds and providing refinements for functions of independent variables using advanced techniques.
Contribution
It introduces near-optimal concentration inequalities for martingales, addressing a missing factor in previous bounds and refining inequalities for independent functions.
Findings
Recovered the missing factor in Freedman-style inequalities
Provided near-optimal bounds for martingales with bounded increments
Refined concentration inequalities for functions of independent variables
Abstract
In this note, we improve some concentration inequalities for martingales with bounded increments. These results recover the missing factor in Freedman-style inequalities and are near optimal. We also provide minor refinements of concentration inequalities for functions of independent random variables. These proofs use techniques from the works of Bentkus and Pinelis.
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 Harmonic Analysis Research
