Revisiting Concentration of Missing Mass
Maciej Skorski
TL;DR
This paper introduces a new method for estimating the concentration of missing mass in heterogenic sums, improving existing bounds and simplifying proofs in the field.
Contribution
It develops a novel approach inspired by Rosenthal's inequality to enhance the bounds on missing mass concentration and simplifies the proof techniques.
Findings
Improved bounds on missing mass concentration.
Simplified proof techniques.
Enhanced understanding of heterogenic sum concentration.
Abstract
We revisit the problem of \emph{missing mass concentration}, developing a new method of estimating concentration of heterogenic sums, in spirit of celebrated Rosenthal's inequality. As a result we slightly improve the state-of-art bounds due to Ben-Hamou at al., and simplify the proofs.
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
TopicsBayesian Methods and Mixture Models · Point processes and geometric inequalities · Probability and Risk Models