Frequentist uncertainty estimates for deep learning.
Year: 2018
Type: preprint
Abstract: We provide frequentist estimates of aleatoric and epistemic uncertainty for deep neural networks. To estimate aleatoric uncertainty we propose simultaneous quantile regression, a loss function to learn all the conditional quantiles of a given target variable. These quantiles lead to well-calibrated prediction intervals. To estimate epistemic uncertainty we propose training certificates, a collection of diverse non-trivial functions that map all training samples to zero. These certificates map out-of-distribution examples to non-zero values, signaling high epistemic uncertainty. We compare our proposals to prior art in various experiments.
Source: arXiv (Cornell University)
Authors: Nataša Tagasovska, David López-Paz
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2898622970