We show that, given data from a mixture of k well-separated spherical Gaussians in Rd, a simple two-round variant of EM will, with high probability, learn the parameters of the Ga...
Abstract--The question of polynomial learnability of probability distributions, particularly Gaussian mixture distributions, has recently received significant attention in theoreti...
In this paper a system was developed for robot behavior acquisition using kinesthetic demonstrations. It enables a humanoid robot to imitate constrained reaching gestures directed...
In this paper, we explore the use of a Gaussian posteriorgram based representation for unsupervised discovery of speech patterns. Compared with our previous work, the new approach...
Given data drawn from a mixture of multivariate Gaussians, a basic problem is to accurately estimate the mixture parameters. We provide a polynomial-time algorithm for this proble...
Adam Tauman Kalai, Ankur Moitra, and Gregory Valia...