Asymptotic analysis of Bayesian generalization error with Newton diagram

DOI10.1016/J.NEUNET.2009.07.029MaRDI QIDQ1784534zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Keisuke Yamazaki, Miki Aoyagi, Sumio Watanabe

Publication date 27 September 2018

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2009.07.029

zbMATH Keywords

Newton diagramBayes generalization errorstatistical singular models

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Algorithmic Learning Theory
• Publication:4955299
• Singularities in mixture models and upper bounds of stochastic complexity.
• Learning Coefficients of Layered Models When the True Distribution Mismatches the Singularities
• Equations of states in singular statistical estimation

Cites work

• scientific article; zbMATH DE number 5957252 (Why is no real title available?)
• scientific article; zbMATH DE number 67623 (Why is no real title available?)
• scientific article; zbMATH DE number 6791314 (Why is no real title available?)
• A decision-theoretic extension of stochastic complexity and its applications to learning
• Algebraic analysis for nonidentifiable learning machines
• Computation and applications of the Newton polyhedrons
• Estimating the dimension of a model
• On the Problem in Model Selection of Neural Network Regression in Overrealizable Scenario
• Resolution of singularities of an algebraic variety over a field of characteristic zero. I
• Singularities in mixture models and upper bounds of stochastic complexity.
• Stochastic complexities of Gaussian mixtures in variational Bayesian approximation
• Stochastic complexities of reduced rank regression in Bayesian estimation
• Stochastic complexity and modeling
• Testing in locally conic models, and application to mixture models
• Variational Bayes Solution of Linear Neural Networks and Its Generalization Performance

Cited in

(13)

• Asymptotic accuracy of Bayes estimation for latent variables with redundancy
• The exact asymptotic form of Bayesian generalization error in latent Dirichlet allocation
• Comparing two Bayes methods based on the free energy functions in Bernoulli mixtures
• Recent advances in algebraic geometry and Bayesian statistics
• Learning Coefficients of Layered Models When the True Distribution Mismatches the Singularities
• An alternative view of variational Bayes and asymptotic approximations of free energy
• Consideration on singularities in learning theory and the learning coefficient
• On equivalent parameter learning in simplified feature space based on Bayesian asymptotic analysis
• A Bayesian learning coefficient of generalization error and Vandermonde matrix-type singularities
• Algorithmic Learning Theory
• A limit theorem in singular regression problem
• Bayesian estimation of multidimensional latent variables and its asymptotic accuracy
• Learning coefficient of generalization error in Bayesian estimation and Vandermonde matrix-type singularity

This page was built for publication: Asymptotic analysis of Bayesian generalization error with Newton diagram

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1784534)