Validation of ML-UQ calibration statistics using simulated reference values: a sensitivity analysis - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Validation of ML-UQ calibration statistics using simulated reference values: a sensitivity analysis

Pascal Pernot

Résumé

Some popular Machine Learning Uncertainty Quantification (ML-UQ) calibration statistics do not have predefined reference values and are mostly used in comparative studies. In consequence, calibration is almost never validated and the diagnostic is left to the appreciation of the reader. Simulated reference values, based on synthetic calibrated datasets derived from actual uncertainties, have been proposed to palliate this problem. As the generative probability distribution for the simulation of synthetic errors is often not constrained, the sensitivity of simulated reference values to the choice of generative distribution might be problematic, shedding a doubt on the calibration diagnostic. This study explores various facets of this problem, and shows that some statistics are excessively sensitive to the choice of generative distribution to be used for validation when the generative distribution is unknown. This is the case, for instance, of the correlation coefficient between absolute errors and uncertainties (CC) and of the expected normalized calibration error (ENCE). A robust validation workflow to deal with simulated reference values is proposed.

Dates et versions

hal-04502356 , version 1 (13-03-2024)

Identifiants

Citer

Pascal Pernot. Validation of ML-UQ calibration statistics using simulated reference values: a sensitivity analysis. 2024. ⟨hal-04502356⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More