Statistical Guarantees for Estimating the Centers of a Two-component Gaussian Mixture by EM

08/07/2016
by   Jason M. Klusowski, et al.
0

Recently, a general method for analyzing the statistical accuracy of the EM algorithm has been developed and applied to some simple latent variable models [Balakrishnan et al. 2016]. In that method, the basin of attraction for valid initialization is required to be a ball around the truth. Using Stein's Lemma, we extend these results in the case of estimating the centers of a two-component Gaussian mixture in d dimensions. In particular, we significantly expand the basin of attraction to be the intersection of a half space and a ball around the origin. If the signal-to-noise ratio is at least a constant multiple of √(d d) , we show that a random initialization strategy is feasible.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/12/2018

Global Convergence of EM Algorithm for Mixtures of Two Component Linear Regression

The Expectation-Maximization algorithm is perhaps the most broadly used ...
research
04/26/2017

Estimating the coefficients of a mixture of two linear regressions by expectation maximization

We give convergence guarantees for estimating the coefficients of a symm...
research
01/14/2021

Optimal Clustering in Anisotropic Gaussian Mixture Models

We study the clustering task under anisotropic Gaussian Mixture Models w...
research
08/28/2019

Randomly initialized EM algorithm for two-component Gaussian mixture achieves near optimality in O(√(n)) iterations

We analyze the classical EM algorithm for parameter estimation in the sy...
research
11/27/2015

Regularized EM Algorithms: A Unified Framework and Statistical Guarantees

Latent variable models are a fundamental modeling tool in machine learni...
research
01/03/2021

Improved Convergence Guarantees for Learning Gaussian Mixture Models by EM and Gradient EM

We consider the problem of estimating the parameters a Gaussian Mixture ...
research
02/15/2022

On the Role of Channel Capacity in Learning Gaussian Mixture Models

This paper studies the sample complexity of learning the k unknown cente...

Please sign up or login with your details

Forgot password? Click here to reset