Strengthened Chernoff-type variance bounds
G. Afendras, N. Papadatos

TL;DR
This paper develops a new class of strengthened Chernoff-type variance bounds for absolutely continuous random variables within the integrated Pearson family, leveraging orthonormal polynomial properties.
Contribution
It introduces novel variance bounds that extend classical Chernoff bounds using orthogonal polynomial techniques for a specific family of distributions.
Findings
New class of variance bounds derived
Bounds applicable to integrated Pearson family
Enhanced bounds compared to classical Chernoff bounds
Abstract
Let be an absolutely continuous random variable from the integrated Pearson family and assume that has finite moments of any order. Using some properties of the associated orthonormal polynomial system, we provide a class of strengthened Chernoff-type variance bounds.
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.
