English

A short note on learning discrete distributions

Statistics Theory 2020-04-10 v3 Probability Statistics Theory

Abstract

The goal of this short note is to provide simple proofs for the "folklore facts" on the sample complexity of learning a discrete probability distribution over a known domain of size kk to various distances ε\varepsilon, with error probability δ\delta.

Keywords

Cite

@article{arxiv.2002.11457,
  title  = {A short note on learning discrete distributions},
  author = {Clément L. Canonne},
  journal= {arXiv preprint arXiv:2002.11457},
  year   = {2020}
}

Comments

This is a review article; its intent is not to provide new results, but instead to gather known (and useful) ones, along with their proofs, in a single convenient location

R2 v1 2026-06-23T13:54:28.882Z