Asymptotic Learning Curve and Renormalizable Condition in Statistical Learning Theory

Abstract

Bayes statistics and statistical physics have the common mathematical structure, where the log likelihood function corresponds to the random Hamiltonian. Recently, it was discovered that the asymptotic learning curves in Bayes estimation are subject to a universal law, even if the log likelihood function can not be approximated by any quadratic form. However, it is left unknown what mathematical property ensures such a universal law. In this paper, we define a renormalizable condition of the statistical estimation problem, and show that, under such a condition, the asymptotic learning curves are ensured to be subject to the universal law, even if the true distribution is unrealizable and singular for a statistical model. Also we study a nonrenormalizable case, in which the learning curves have the different asymptotic behaviors from the universal law.

References in corpus (2)

• On real log canonical thresholds
• Equations of States in Statistical Learning for a Nonparametrizable and Regular Case

Cited by in corpus (5)

• Asymptotic Equivalence of Bayes Cross Validation and Widely Applicable Information Criterion in Singular Learning Theory
• A Widely Applicable Bayesian Information Criterion
• Simultaneous Estimation of Noise Variance and Number of Peaks in Bayesian Spectral Deconvolution
• Large Deviation Strategy for Inverse Problem
• The Quantum Relative Entropy as a Rate Function and Information Criteria