Guardado en:
Detalles Bibliográficos
Autores principales: Adipoetra, Michael, Martin, Ségolène
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2501.07358
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910782170595328
author Adipoetra, Michael
Martin, Ségolène
author_facet Adipoetra, Michael
Martin, Ségolène
contents We propose a novel deep clustering method that integrates Variational Autoencoders (VAEs) into the Expectation-Maximization (EM) framework. Our approach models the probability distribution of each cluster with a VAE and alternates between updating model parameters by maximizing the Evidence Lower Bound (ELBO) of the log-likelihood and refining cluster assignments based on the learned distributions. This enables effective clustering and generation of new samples from each cluster. Unlike existing VAE-based methods, our approach eliminates the need for a Gaussian Mixture Model (GMM) prior or additional regularization techniques. Experiments on MNIST and FashionMNIST demonstrate superior clustering performance compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2501_07358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Generative Clustering with VAEs and Expectation-Maximization
Adipoetra, Michael
Martin, Ségolène
Machine Learning
We propose a novel deep clustering method that integrates Variational Autoencoders (VAEs) into the Expectation-Maximization (EM) framework. Our approach models the probability distribution of each cluster with a VAE and alternates between updating model parameters by maximizing the Evidence Lower Bound (ELBO) of the log-likelihood and refining cluster assignments based on the learned distributions. This enables effective clustering and generation of new samples from each cluster. Unlike existing VAE-based methods, our approach eliminates the need for a Gaussian Mixture Model (GMM) prior or additional regularization techniques. Experiments on MNIST and FashionMNIST demonstrate superior clustering performance compared to state-of-the-art methods.
title Deep Generative Clustering with VAEs and Expectation-Maximization
topic Machine Learning
url https://arxiv.org/abs/2501.07358