Work

A Probabilistic Analysis of EM for Mixtures of Separated, Spherical Gaussians

Year: 2007

Type: article

Abstract: We show that, given data from a mixture of k well-separated spherical Gaussians in ℜ^d, a simple two-round variant of EM will, with high probability, learn the parameters of the Gaussians to near-optimal precision, if the dimension is high (d >> ln k). We relate this to previous theoretical and empirical work on the EM algorithm.

Source: CaltechAUTHORS (California Institute of Technology)

DOI: 10.5555/1248659.1248666

Authors: Sanjoy Dasgupta, Leonard J. Schulman

Language: English

Topic: Bayesian Methods and Mixture Models

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Award: CAREER: Algorithms for Unsupervised Learning

OpenAlex ID: W2146758737