Information-theoretic Generalization Analysis for Expected Calibration Error

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Futami, Futoshi, Fujisawa, Masahiro
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909622624845824
author Futami, Futoshi
Fujisawa, Masahiro
author_facet Futami, Futoshi
Fujisawa, Masahiro
contents While the expected calibration error (ECE), which employs binning, is widely adopted to evaluate the calibration performance of machine learning models, theoretical understanding of its estimation bias is limited. In this paper, we present the first comprehensive analysis of the estimation bias in the two common binning strategies, uniform mass and uniform width binning. Our analysis establishes upper bounds on the bias, achieving an improved convergence rate. Moreover, our bounds reveal, for the first time, the optimal number of bins to minimize the estimation bias. We further extend our bias analysis to generalization error analysis based on the information-theoretic approach, deriving upper bounds that enable the numerical evaluation of how small the ECE is for unknown data. Experiments using deep learning models show that our bounds are nonvacuous thanks to this information-theoretic generalization analysis approach.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15709
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Information-theoretic Generalization Analysis for Expected Calibration Error
Futami, Futoshi
Fujisawa, Masahiro
Machine Learning
Statistics Theory
While the expected calibration error (ECE), which employs binning, is widely adopted to evaluate the calibration performance of machine learning models, theoretical understanding of its estimation bias is limited. In this paper, we present the first comprehensive analysis of the estimation bias in the two common binning strategies, uniform mass and uniform width binning. Our analysis establishes upper bounds on the bias, achieving an improved convergence rate. Moreover, our bounds reveal, for the first time, the optimal number of bins to minimize the estimation bias. We further extend our bias analysis to generalization error analysis based on the information-theoretic approach, deriving upper bounds that enable the numerical evaluation of how small the ECE is for unknown data. Experiments using deep learning models show that our bounds are nonvacuous thanks to this information-theoretic generalization analysis approach.
title Information-theoretic Generalization Analysis for Expected Calibration Error
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2405.15709