Improved convergence guarantees for learning Gaussian mixture models by EM and gradient EM

DOI10.1214/21-EJS1905zbMath1471.62273arXiv2101.00575OpenAlexW3204209514MaRDI QIDQ2233582

Boaz Nadler, Nimrod Segol

Publication date: 11 October 2021

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2101.00575

zbMATH Keywords

EM algorithmGaussian mixture models

Mathematics Subject Classification ID

Point estimation (62F10) Parametric inference (62F99)

Cites Work

• Unnamed Item
• Unnamed Item
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• A spectral algorithm for learning mixture models
• On the convergence properties of the EM algorithm
• Learning mixtures of separated nonspherical Gaussians
• Statistical convergence of the EM algorithm on Gaussian mixture models
• Efficiently learning mixtures of two Gaussians
• Tight Bounds for Learning a Mixture of Two Gaussians
• Learning mixtures of spherical gaussians
• The Spectral Method for General Mixture Models
• High-Dimensional Probability
• Learning Theory

This page was built for publication: Improved convergence guarantees for learning Gaussian mixture models by EM and gradient EM