Optimal Robust Learning of Discrete Distributions from Batches
Abstract
Many applications, including natural language processing, sensor networks, collaborative filtering, and federated learning, call for estimating discrete distributions from data collected in batches, some of which may be untrustworthy, erroneous, faulty, or even adversarial. Previous estimators for this setting ran in exponential time, and for some regimes required a suboptimal number of batches. We provide the first polynomial-time estimator that is optimal in the number of batches and achieves essentially the best possible estimation accuracy.
Cite
Text
Jain and Orlitsky. "Optimal Robust Learning of Discrete Distributions from Batches." International Conference on Machine Learning, 2020.Markdown
[Jain and Orlitsky. "Optimal Robust Learning of Discrete Distributions from Batches." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/jain2020icml-optimal/)BibTeX
@inproceedings{jain2020icml-optimal,
title = {{Optimal Robust Learning of Discrete Distributions from Batches}},
author = {Jain, Ayush and Orlitsky, Alon},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {4651-4660},
volume = {119},
url = {https://mlanthology.org/icml/2020/jain2020icml-optimal/}
}