Bayesian averaging of computer models with domain discrepancies: a nuclear physics perspective
This article studies Bayesian model averaging (BMA) in the context of several competing computer models in nuclear physics. We quantify model uncertainty in terms of posterior prediction errors, including an explicit formula for their posterior variance. We extend BMA when the competing models are defined on non-identical study regions. Any model's local forecasting difficulty is offset by predictions obtained from the average model, extending individual models to the full domain. We illustrate our methodology via simulations and applications to forecasting nuclear masses. We find significant improvement in both the BMA prediction error and the quality of the corresponding uncertainty quantification.
READ FULL TEXT