acm-header
Sign In

Communications of the ACM

Latest Research


Latest Research Research Archive Refine your search:
subjectTheory
author Ankur Moitra

Robustness Meets Algorithms
From Communications of the ACM

Robustness Meets Algorithms

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...

Learning Topic Models - Provably and Efficiently
From Communications of the ACM

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.

Disentangling Gaussians
From Communications of the ACM

Disentangling Gaussians

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...
Sign In for Full Access
» Forgot Password? » Create an ACM Web Account