General Bayesian L2 calibration of mathematical models

Abstract: A mathematical model is a representation of a physical system depending on unknown parameters. Calibration refers to attributing values to these parameters, using observations of the physical system, acknowledging that the mathematical model is an inexact representation of the physical system. General Bayesian inference generalizes traditional Bayesian inference by replacing the log-likelihood in Bayes' theorem by a (negative) loss function. Methodology is proposed for the general Bayesian calibration of mathematical models where the resulting posterior distributions estimate the values of the parameters that minimize the L2 norm of the difference between the mathematical model and true physical system.