Foundation of Calculating Normalized Maximum Likelihood for Continuous Probability Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Suzuki, Atsushi, Fukuzawa, Kota, Yamanishi, Kenji
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914948327669760
author Suzuki, Atsushi
Fukuzawa, Kota
Yamanishi, Kenji
author_facet Suzuki, Atsushi
Fukuzawa, Kota
Yamanishi, Kenji
contents The normalized maximum likelihood (NML) code length is widely used as a model selection criterion based on the minimum description length principle, where the model with the shortest NML code length is selected. A common method to calculate the NML code length is to use the sum (for a discrete model) or integral (for a continuous model) of a function defined by the distribution of the maximum likelihood estimator. While this method has been proven to correctly calculate the NML code length of discrete models, no proof has been provided for continuous cases. Consequently, it has remained unclear whether the method can accurately calculate the NML code length of continuous models. In this paper, we solve this problem affirmatively, proving that the method is also correct for continuous cases. Remarkably, completing the proof for continuous cases is non-trivial in that it cannot be achieved by merely replacing the sums in discrete cases with integrals, as the decomposition trick applied to sums in the discrete model case proof is not applicable to integrals in the continuous model case proof. To overcome this, we introduce a novel decomposition approach based on the coarea formula from geometric measure theory, which is essential to establishing our proof for continuous cases.
format Preprint
id arxiv_https___arxiv_org_abs_2409_08387
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Foundation of Calculating Normalized Maximum Likelihood for Continuous Probability Models
Suzuki, Atsushi
Fukuzawa, Kota
Yamanishi, Kenji
Statistics Theory
Information Theory
Machine Learning
The normalized maximum likelihood (NML) code length is widely used as a model selection criterion based on the minimum description length principle, where the model with the shortest NML code length is selected. A common method to calculate the NML code length is to use the sum (for a discrete model) or integral (for a continuous model) of a function defined by the distribution of the maximum likelihood estimator. While this method has been proven to correctly calculate the NML code length of discrete models, no proof has been provided for continuous cases. Consequently, it has remained unclear whether the method can accurately calculate the NML code length of continuous models. In this paper, we solve this problem affirmatively, proving that the method is also correct for continuous cases. Remarkably, completing the proof for continuous cases is non-trivial in that it cannot be achieved by merely replacing the sums in discrete cases with integrals, as the decomposition trick applied to sums in the discrete model case proof is not applicable to integrals in the continuous model case proof. To overcome this, we introduce a novel decomposition approach based on the coarea formula from geometric measure theory, which is essential to establishing our proof for continuous cases.
title Foundation of Calculating Normalized Maximum Likelihood for Continuous Probability Models
topic Statistics Theory
Information Theory
Machine Learning
url https://arxiv.org/abs/2409.08387