We give the first efficient algorithm for estimating the parameters of a high-dimensional Gaussian that is able to tolerate a constant fraction of corruptions that...Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Ankur Moitra, Alistair Stewart From Communications of the ACM | May 2021
This article shows that some new theoretical algorithms that have provable guarantees can be adapted to yield highly practical tools for topic modeling.
Sanjeev Arora, Rong Ge, Yoni Halpern, David Mimno, Ankur Moitra, David Sontag, Yichen Wu, Michael Zhu From Communications of the ACM | April 2018
The Gaussian mixture model is one of the oldest and most widely used statistical models. Our work focuses on the case where the mixture consists of a small but...Adam Tauman Kalai, Ankur Moitra, Gregory Valiant From Communications of the ACM | February 2012