Bayesian Generalization Error of Poisson Mixture and Simplex Vandermonde Matrix Type Singularity
Statistics Theory
2020-01-01 v1 Statistics Theory
Abstract
A Poisson mixture is one of the practically important models in computer science, biology, and sociology. However, the theoretical property has not been studied because the posterior distribution can not be approximated by any normal distribution. Such a model is called singular and it is known that Real Log Canonical Threshold (RLCT) is equal to the coefficient of the asymptotically main term of the Bayesian generalization error. In this paper, we derive RLCT of a simplex Vandermonde matrix type singularity which is equal to that of a Poisson mixture in general cases.
Cite
@article{arxiv.1912.13289,
title = {Bayesian Generalization Error of Poisson Mixture and Simplex Vandermonde Matrix Type Singularity},
author = {Kenichiro Sato and Sumio Watanabe},
journal= {arXiv preprint arXiv:1912.13289},
year = {2020}
}
Comments
33 pages