mlsanityData to 7 Oct 2026

Concentration Bounds for Discrete Distribution Estimation in KL Divergence

arXiv 2302.06869 ↗First posted 14 Feb 2023stat.ML cs.DM cs.ITcited by 6

Not on the map. Why?

Abstract (arXiv)

We study the problem of discrete distribution estimation in KL divergence and provide concentration bounds for the Laplace estimator. We show that the deviation from mean scales as √k/n when n ≥ k, improving upon the best prior result of k/n. We also establish a matching lower bound that shows that our bounds are tight up to polylogarithmic factors.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 3 of its 21 references that are in the map. First posted on arXiv 14 Feb 2023.

Builds on

3 of 21 references.

References · 3

  1. 2020Fast active learning for pure exploration in reinforcement learningcited by 92
  2. 2019An improper estimator with optimal excess risk in misspecified density estimation and logistic regressioncited by 24
  3. 2020Near-Optimal Learning of Tree-Structured Distributions by Chow-Liucited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 2; 2026: 1.

6 papers.

  1. 2023High-Probability Risk Bounds via Sequential Predictorscited by 9
  2. 2023Near-Optimal Degree Testing for Bayes Netscited by 3
  3. 2025Nearly Minimax Discrete Distribution Estimation in Kullback-Leibler Divergence with High Probabilitycited by 3
  4. 2024On the KL-Divergence-based Robust Satisficing Modelcited by 1
  5. 2026Ratio Covers of Convex Sets and Optimal Mixture Density Estimationcited by 1
  6. 2025Online Episodic Convex Reinforcement Learningcited by 0