Learning continuous latent variable models with Bregman divergences

DOI10.1007/B14273MaRDI QIDQ5897387zbMATH OpenOpenAlexFDO

Authors Shaojun Wang, D. Schuurmans

Publication date 23 February 2010

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/b14273

zbMATH Keywords

alternating minimizationbackward projectionBregman divergenceforward projectioninformation geometryiterative scalingstatistical machine learningunsupervised learning

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Learning and adaptive systems in artificial intelligence (68T05) Measures of information, entropy (94A17)

Recommendations

• Clustering with Bregman divergences.
• Learning algorithms for enclosing points in Bregmanian spheres.
• A modified EM algorithm for mixture models based on Bregman divergence
• A new method of moments for latent variable models
• Advanced Lectures on Machine Learning

Cited in

(5)

• Infinite-dimensional gradient-based descent for alpha-divergence minimisation
• Transfer latent variable model based on divergence analysis
• Posterior regularization for structured latent variable models
• Learning algorithms for enclosing points in Bregmanian spheres.
• Learning joint latent representations based on information maximization

This page was built for publication: Learning continuous latent variable models with Bregman divergences

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5897387)