Timezone: »

 
Poster
Optimal Robust Learning of Discrete Distributions from Batches
Ayush Jain · Alon Orlitsky

Tue Jul 14 10:00 AM -- 10:45 AM & Tue Jul 14 09:00 PM -- 09:45 PM (PDT) @
in Poster Session 4 »

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.

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

Author Information

Ayush Jain (UC San Diego)
Alon Orlitsky (UCSD)

More from the Same Authors