paper-with-me

Papers

Convergence of Gradient EM on Multi-component Mixture of Gaussians

2017-12-01 · NeurIPS 2017 12 · Bowei Yan, Mingzhang Yin, Purnamrita Sarkar

In this paper, we study convergence properties of the gradient variant of Expectation-Maximization algorithm~\cite{lange1995gradient} for Gaussian Mixture Models for arbitrary number of clusters and mixing coefficients. We derive the convergence rate depending on the mixing coefficients, minimum and maximum pairwise distances between the true centers, dimensionality and number of components; and obtain a near-optimal local contraction radius. While there have been some recent notable works that derive local convergence rates for EM in the two symmetric mixture of Gaussians, in the more general case, the derivations need structurally different and non-trivial arguments. We use recent tools from learning theory and empirical processes to achieve our theoretical results.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Learning Theory

Similar Papers 제목 키워드 기반

Variational Inference with Mixtures of Isotropic Gaussians

2025-06-16 · Marguerite Petit-Talamon, Marc Lambert, Anna Korba

Variational inference (VI) is a popular approach in Bayesian inference, that looks for the best approximation of the posterior distribution within a parametric family, minimizing a loss that is typically the (reverse) Ku…

Bayesian InferenceVariational Inference

Tight bounds for learning a mixture of two gaussians

2014-04-19 · Moritz Hardt, Eric Price

We consider the problem of identifying the parameters of an unknown mixture of two arbitrary $d$-dimensional gaussians from a sequence of independent random samples. Our main results are upper and lower bounds giving a c…

Dimensionality ReductionVocal Bursts Valence Prediction

Convergence Analysis of Gradient EM for Multi-component Gaussian Mixture

2017-05-23 · Bowei Yan, Mingzhang Yin, Purnamrita Sarkar

In this paper, we study convergence properties of the gradient Expectation-Maximization algorithm \cite{lange1995gradient} for Gaussian Mixture Models for general number of clusters and mixing coefficients. We derive the…

Learning Theory

Natural Gradient Variational Inference with Gaussian Mixture Models

2021-11-15 · Farzaneh Mahdisoltani

Bayesian methods estimate a measure of uncertainty by using the posterior distribution. One source of difficulty in these methods is the computation of the normalizing constant. Calculating exact posterior is generally i…

Variational Inference

Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models

2024-06-29 · Weihang Xu, Maryam Fazel, Simon S. Du

We study the gradient Expectation-Maximization (EM) algorithm for Gaussian Mixture Models (GMM) in the over-parameterized setting, where a general GMM with $n>1$ components learns from data that are generated by a single…