English

An Effective Bernstein-type Bound on Shannon Entropy over Countably Infinite Alphabets

Information Theory 2021-06-24 v1 math.IT Probability

Abstract

We prove a Bernstein-type bound for the difference between the average of negative log-likelihoods of independent discrete random variables and the Shannon entropy, both defined on a countably infinite alphabet. The result holds for the class of discrete random variables with tails lighter than or on the same order of a discrete power-law distribution. Most commonly-used discrete distributions such as the Poisson distribution, the negative binomial distribution, and the power-law distribution itself belong to this class. The bound is effective in the sense that we provide a method to compute the constants in it.

Keywords

Cite

@article{arxiv.2106.12149,
  title  = {An Effective Bernstein-type Bound on Shannon Entropy over Countably Infinite Alphabets},
  author = {Yunpeng Zhao},
  journal= {arXiv preprint arXiv:2106.12149},
  year   = {2021}
}
R2 v1 2026-06-24T03:29:37.610Z