Bayesian estimation of multidimensional latent variables and its asymptotic accuracy

DOI10.1016/j.neunet.2018.03.002zbMath1434.68478DBLPjournals/nn/Yamazaki18arXiv1510.01003OpenAlexW2963259719WikidataQ62496109 ScholiaQ62496109MaRDI QIDQ2181075

Keisuke Yamazaki

Publication date: 18 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1510.01003

zbMATH Keywords

singularitiesBayesian statisticsunsupervised learningalgebraic geometryhierarchical parametric models

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Asymptotic accuracy of Bayes estimation for latent variables with redundancy
• 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
• 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
• Ideal-Theoretic Strategies for Asymptotic Approximation of Marginal Likelihood Integrals
• Algebraic Geometry and Statistical Learning Theory
• An asymptotic approximation of the marginal likelihood for general Markov models

This page was built for publication: Bayesian estimation of multidimensional latent variables and its asymptotic accuracy