Adversarially Learned Mixture Model

The Adversarially Learned Mixture Model (AMM) is a generative model for unsupervised or semi-supervised data clustering. The AMM is the first adversarially optimized method to model the conditional dependence between inferred continuous and categorical latent variables. Experiments on the MNIST and...

Full description

Saved in:
Bibliographic Details
Main Authors Jesson, Andrew, Low-Kam, Cécile, Nair, Tanya, Soudan, Florian, Chandelier, Florent, Chapados, Nicolas
Format Journal Article
LanguageEnglish
Published 14.07.2018
Subjects
Computer Science - Learning
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary:The Adversarially Learned Mixture Model (AMM) is a generative model for unsupervised or semi-supervised data clustering. The AMM is the first adversarially optimized method to model the conditional dependence between inferred continuous and categorical latent variables. Experiments on the MNIST and SVHN datasets show that the AMM allows for semantic separation of complex data when little or no labeled data is available. The AMM achieves a state-of-the-art unsupervised clustering error rate of 2.86% on the MNIST dataset. A semi-supervised extension of the AMM yields competitive results on the SVHN dataset.
DOI:10.48550/arxiv.1807.05344