.png){kind=icon}
Return
Calibrating Bayesian generative machine learning for Bayesiamplification
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/ad9136.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, combinations of generative and Bayesian deep learning have been introduced in particle physics for both fast detector simulation and inference tasks. These neural networks aim to quantify the uncertainty on the generated distribution originating from limited training statistics. The interpretation of a distribution-wide uncertainty however remains ill-defined. We show a clear scheme for quantifying the calibration of Bayesian generative machine learning models. For a Continuous Normalizing Flow applied to a low-dimensional toy example, we evaluate the calibration of Bayesian uncertainties from either a mean-field Gaussian weight posterior, or Monte Carlo sampling network weights, to gauge their behaviour on unsteady distribution edges. Well calibrated uncertainties can then be used to roughly estimate the number of uncorrelated truth samples that are equivalent to the generated sample and clearly indicate data amplification for smooth features of the distribution.
Keywords:
Bayesian neural networks
generative neural networks
data amplification
fast detector simulation
Journal
M
IF:
4.6
Papers:
1.1K
Citations:
3.4K
Organization
View more organizations
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSaveShareSave
ShareSave View more