Equations of States in Statistical Learning for a Nonparametrizable and Regular Case

Abstract

Many learning machines that have hierarchical structure or hidden variables are now being used in information science, artificial intelligence, and bioinformatics. However, several learning machines used in such fields are not regular but singular statistical models, hence their generalization performance is still left unknown. To overcome these problems, in the previous papers, we proved new equations in statistical learning, by which we can estimate the Bayes generalization loss from the Bayes training loss and the functional variance, on the condition that the true distribution is a singularity contained in a learning machine. In this paper, we prove that the same equations hold even if a true distribution is not contained in a parametric model. Also we prove that, the proposed equations in a regular case are asymptotically equivalent to the Takeuchi information criterion. Therefore, the proposed equations are always applicable without any condition on the unknown true distribution.

References in corpus (2)

• Equations of States in Singular Statistical Estimation
• A Limit Theorem in Singular Regression Problem

Cited by in corpus (5)

• Asymptotic Equivalence of Bayes Cross Validation and Widely Applicable Information Criterion in Singular Learning Theory
• Approximating Cross-validatory Predictive Evaluation in Bayesian Latent Variables Models with Integrated IS and WAIC
• Asymptotic Learning Curve and Renormalizable Condition in Statistical Learning Theory
• Uncertainty in Bayesian Leave-One-Out Cross-Validation Based Model Comparison
• Prediction Errors for Penalized Regressions based on Generalized Approximate Message Passing