Optimal Robust Learning of Discrete Distributions from Batches

Part of Proceedings of the International Conference on Machine Learning 1 pre-proceedings (ICML 2020)

Bibtex »Metadata »Paper »Supplemental »

Bibtek download is not availble in the pre-proceeding


Ayush Jain, Alon Orlitsky


<p>Many applications, including natural language processing, sensor networks, collaborative filtering, and federated learning, call for estimating distributions from data collected in batches, some of which may be untrustworthy, erroneous, faulty, or even adversarial.</p> <p>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.</p>