Uncertainty Quantification via Stable Distribution Propagation

Published: 16 Jan 2024, Last Modified: 22 Mar 2024ICLR 2024 posterEveryoneRevisionsBibTeX
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: propagating distributions, uncertainty, uncertainties, aleatoric, epistemic, moment matching, total variation, sampling-free, deterministic, variational inference, propagation, probabilistic neural networks, variance propagation, Cauchy, Cauchy distribution, Gaussian, analytical, data uncertainty, alpha stable
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Abstract: We propose a new approach for propagating stable probability distributions through neural networks. Our method is based on local linearization, which we show to be an optimal approximation in terms of total variation distance for the ReLU non-linearity. This allows propagating Gaussian and Cauchy input uncertainties through neural networks to quantify their output uncertainties. To demonstrate the utility of propagating distributions, we apply the proposed method to predicting calibrated confidence intervals and selective prediction on out-of-distribution data. The results demonstrate a broad applicability of propagating distributions and show the advantages of our method over other approaches such as moment matching.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)
Submission Number: 4440