Generative models uncertainty estimation

In recent years fully-parametric fast simulation methods based on generative models have been proposed for a variety of high-energy physics detectors. By their nature, the quality data-driven degrades in regions phase space where data are sparse. Since machine-learning hard to analyse from physical principles, commonly used testing procedures performed way and can't be reliably such regions. our work we propose three estimate uncertainty inside outside training region, along with calibration techniques. A test LHCb RICH is also presented.