Asymptotic accuracy of Bayes estimation for latent variables with redundancy

DOI10.1007/s10994-015-5482-3zbMath1351.68241arXiv1205.3234OpenAlexW2034024264MaRDI QIDQ255357

Keisuke Yamazaki

Publication date: 9 March 2016

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

Full work available at URL: https://arxiv.org/abs/1205.3234

zbMATH Keywords

singularitiesunsupervised learningalgebraic geometryBayes statisticshierarchical parametric models

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Information criteria and cross validation for Bayesian inference in regular and singular cases, Bayesian estimation of multidimensional latent variables and its asymptotic accuracy, Recent advances in algebraic geometry and Bayesian statistics, Effects of additional data on Bayesian clustering

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Comparing two Bayes methods based on the free energy functions in Bernoulli mixtures
• Identifiability of parameters in latent structure models with many observed variables
• Stochastic complexity and modeling
• Estimating the dimension of a model
• Hyper Markov laws in the statistical analysis of decomposable graphical models
• Singularities in mixture models and upper bounds of stochastic complexity.
• Asymptotic analysis of Bayesian generalization error with Newton diagram
• Convergence rates of posterior distributions.
• Convergence of latent mixing measures in finite and infinite mixture models
• Convergence of estimates under dimensionality restrictions
• Stochastic complexities of reduced rank regression in Bayesian estimation
• Resolution of singularities of an algebraic variety over a field of characteristic zero. I
• Algebraic Analysis for Nonidentifiable Learning Machines
• Algebraic Geometry and Statistical Learning Theory
• An asymptotic approximation of the marginal likelihood for general Markov models
• Resolution of Singularities and Division of Distributions
• A new look at the statistical model identification