Comparing two Bayes methods based on the free energy functions in Bernoulli mixtures

DOI10.1016/J.NEUNET.2013.03.002MaRDI QIDQ459428zbMATH OpenOpenAlexWikidataFDO

Authors Keisuke Yamazaki, Daisuke Kaji

Publication date 9 October 2014

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2013.03.002

zbMATH Keywords

phase transitionalgebraic geometrymean field approximationvariational Bayes method

Mathematics Subject Classification ID

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

Recommendations

• An alternative view of variational Bayes and asymptotic approximations of free energy
• Free energy methods for Bayesian inference: efficient exploration of univariate Gaussian mixture posteriors
• Upper bound for variational free energy of Bayesian networks
• Stochastic complexities of general mixture models in variational Bayesian learning
• Algorithmic Learning Theory

Cites work

• scientific article; zbMATH DE number 5957252 (Why is no real title available?)
• Algebraic Geometry and Statistical Learning Theory
• Algebraic analysis for nonidentifiable learning machines
• An introduction to MCMC for machine learning
• Asymptotic analysis of Bayesian generalization error with Newton diagram
• Condition for perfect dimensionality recovery by variational Bayesian PCA
• Estimating the dimension of a model
• Learning coefficient of generalization error in Bayesian estimation and Vandermonde matrix-type singularity
• Singularities in mixture models and upper bounds of stochastic complexity.
• Stochastic complexities of Gaussian mixtures in variational Bayesian approximation
• Stochastic complexities of general mixture models in variational Bayesian learning
• Stochastic complexity and generalization error of a restricted Boltzmann machine in Bayesian estimation
• Stochastic complexity and modeling
• Theoretical analysis of Bayesian matrix factorization
• Upper bound for variational free energy of Bayesian networks

Cited in

(7)

• Information criteria and cross validation for Bayesian inference in regular and singular cases
• Asymptotic accuracy of Bayes estimation for latent variables with redundancy
• Recent advances in algebraic geometry and Bayesian statistics
• Bayesian estimation of multidimensional latent variables and its asymptotic accuracy
• Comparison study between {MCMC}-based and weight-based Bayesian methods for identification of joint distribution
• Free energy methods for Bayesian inference: efficient exploration of univariate Gaussian mixture posteriors
• Variational approximation error in non-negative matrix factorization

This page was built for publication: Comparing two Bayes methods based on the free energy functions in Bernoulli mixtures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q459428)