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 is independent of the dimension.
Ankur Moitra
Advertisement
Author Archives
Learning Topic Models – Provably and Efficiently
This article shows that some new theoretical algorithms that have provable guarantees can be adapted to yield highly practical tools for topic modeling.
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 unknown number of Gaussian "components" that may overlap
Shape the Future of Computing
ACM encourages its members to take a direct hand in shaping the future of the association. There are more ways than ever to get involved.
Get Involved