An alternative view of variational Bayes and asymptotic approximations of free energy

DOI10.1007/s10994-011-5264-5zbMath1246.68191OpenAlexW2145616149MaRDI QIDQ420913

Kazuho Watanabe

Publication date: 23 May 2012

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-011-5264-5

zbMATH Keywords

asymptotic analysisvariational Bayesgeneralization errorlocal variation approximationvariational free energy

Mathematics Subject Classification ID

Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Variational approximation error in non-negative matrix factorization

Uses Software

• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic complexities of general mixture models in variational Bayesian learning
• Upper bound for variational free energy of Bayesian networks
• Estimating the dimension of a model
• Singularities in mixture models and upper bounds of stochastic complexity.
• Asymptotic analysis of Bayesian generalization error with Newton diagram
• An introduction to variational methods for graphical models
• Divergence measures and a general framework for local variational approximation
• Stochastic complexities of reduced rank regression in Bayesian estimation
• Algebraic Geometry and Statistical Learning Theory
• Variational Bayes Solution of Linear Neural Networks and Its Generalization Performance

This page was built for publication: An alternative view of variational Bayes and asymptotic approximations of free energy