Elementary Tail Bounds on the Hypergeometric Distribution

TL;DR

This paper introduces simple and improved concentration bounds for the hypergeometric distribution, demonstrating their advantages over existing bounds in various regimes.

Contribution

It presents new, straightforward tail bounds for the hypergeometric distribution that outperform previous results in multiple scenarios.

Findings

Derived two new concentration bounds for hypergeometric distribution

Compared new bounds with existing results showing improved performance

Applicable across different regimes of the hypergeometric distribution

Abstract

We use a simple method to derive two concentration bounds on the hypergeometric distribution. Comparison with existing results illustrates the advantage of these bounds across different regimes.