Ten Steps of EM Suffice for Mixtures of Two Gaussians

نویسندگان

  • Constantinos Daskalakis
  • Christos Tzamos
  • Manolis Zampetakis
چکیده

We provide global convergence guarantees for the expectation-maximization (EM) algorithm applied to mixtures of two Gaussians with known covariance matrices. We show that EM converges geometrically to the correct mean vectors, and provide simple, closed-form expressions for the convergence rate. As a simple illustration, we show that in one dimension ten steps of the EM algorithm initialized at +∞ result in less than 1% error estimation of the means.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

EM for Spherical Gaussians

In this project, we examine two aspects of the behavior of the EM algorithm for mixtures of spherical Gaussians; 1) the benefit of spectral projection for such mixtures, and 2) the general behavior of the EM algorithm under certain separability criteria. Our current results are for mixtures of two Gaussians, although these can be extended. In the case of 1), we show that the value of the Q func...

متن کامل

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

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 Gaussians to nearoptimal precision, if the dimension is high (d lnk). We relate this to previous theoretical and empirical work on the EM algorithm.

متن کامل

A Two-Round Variant of EM for Gaussian Mixtures

We show that, given data from a mixture of k well-separated spherical Gaussians in !Rn, a sim­ ple two-round variant of EM will, with high probability, learn the centers of the Gaussians to near-optimal precision, if the dimension is high (n » log k). We relate this to previous theoreti­ cal and empirical work on the EM algorithm.

متن کامل

Modeling the Surface Tension and the Interface of Ten Selected Liquid Mixtures: Correlation, Prediction, and the Influence of Using Partial Molar Volume

This work investigates the modeling of the surface tension and the interface of liquid mixtures. Nine binary liquid mixtures of (DMSO+alcohols), (2-Propanol+2,2,4-trimethylpentane), (Tetrahydrofuran+2-Propanol), (Tetrahydrofuran+2,2,4-trimethylpentane), and (ethano+glycerol) are considered. Additionally, one ternary liquid mixture of (Tetrahydrofuran+2-Propanol+2,2,4-trimethylpenta...

متن کامل

Global Analysis of Expectation Maximization for Mixtures of Two Gaussians

Expectation Maximization (EM) is among the most popular algorithms for estimating parameters of statistical models. However, EM, which is an iterative algorithm based on the maximum likelihood principle, is generally only guaranteed to find stationary points of the likelihood objective, and these points may be far from any maximizer. This article addresses this disconnect between the statistica...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017