A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
Predictive uncertainties can be characterized by two properties--calibration and sharpness. This paper argues for reasoning about uncertainty in terms these properties and proposes simple algorithms for enforcing them in deep learning. Our methods focus on the strongest notion of calibration--distribution calibration--and enforce it by fitting a low-dimensional density or quantile function with a neural estimator. The resulting approach is much simpler and more broadly applicable than previousarXiv:2112.07184v1 fatcat:qaw6we4azjcgvg26acudtyazre