Skip to yearly menu bar Skip to main content


Optimal Robust Learning of Discrete Distributions from Batches

Ayush Jain · Alon Orlitsky

Keywords: [ Information Theory and Estimation ] [ Non-parametric Methods ] [ Robust Statistics and Machine Learning ] [ Trustworthy Machine Learning ]


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.

Chat is not available.