A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions
Abstract
Symmetric distribution properties such as support size, support coverage, entropy, and proximity to uniformity, arise in many applications. Recently, researchers applied different estimators and analysis tools to derive asymptotically sample-optimal approximations for each of these properties. We show that a single, simple, plug-in estimator—profile maximum likelihood (PML)—is sample competitive for all symmetric properties, and in particular is asymptotically sample-optimal for all the above properties.
Cite
Text
Acharya et al. "A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions." International Conference on Machine Learning, 2017.Markdown
[Acharya et al. "A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions." International Conference on Machine Learning, 2017.](https://mlanthology.org/icml/2017/acharya2017icml-unified/)BibTeX
@inproceedings{acharya2017icml-unified,
title = {{A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions}},
author = {Acharya, Jayadev and Das, Hirakendu and Orlitsky, Alon and Suresh, Ananda Theertha},
booktitle = {International Conference on Machine Learning},
year = {2017},
pages = {11-21},
volume = {70},
url = {https://mlanthology.org/icml/2017/acharya2017icml-unified/}
}