A Bayesian Learning Coefficient of Generalization Error and Vandermonde Matrix-Type Singularities

DOI10.1080/03610920903094899zbMath1272.62010OpenAlexW1965125272MaRDI QIDQ2786256

Miki Aoyagi

Publication date: 21 September 2010

Published in: Communications in Statistics - Theory and Methods (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/03610920903094899

zbMATH Keywords

resolution of singularitieszeta functiongeneralization errornormal mixture modelshierarchical learning models

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Sampling theory, sample surveys (62D05) Computational aspects of higher-dimensional varieties (14Q15) Invariants of analytic local rings (32S10)

Related Items (5)

Consideration on singularities in learning theory and the learning coefficient ⋮ Learning Coefficient of Generalization Error in Bayesian Estimation and Vandermonde Matrix-Type Singularity ⋮ Consideration on the learning efficiency of multiple-layered neural networks with linear units ⋮ Identifying the number of components in Gaussian mixture models using numerical algebraic geometry ⋮ Singularity Structures and Impacts on Parameter Estimation in Finite Mixtures of Distributions

Cites Work

• Stochastic complexity and modeling
• Estimating the dimension of a model
• Singularities in mixture models and upper bounds of stochastic complexity.
• Collusion through mediated communication in repeated games with imperfect private monitoring
• Asymptotic analysis of Bayesian generalization error with Newton diagram
• Asymptotic behavior of exchange ratio in exchange Monte Carlo method
• 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
• Universal coding, information, prediction, and estimation
• Singularities of pairs via jet schemes
• Singularities of Pairs
• A decision-theoretic extension of stochastic complexity and its applications to learning
• A new look at the statistical model identification

This page was built for publication: A Bayesian Learning Coefficient of Generalization Error and Vandermonde Matrix-Type Singularities