Volltext-Downloads (blau) und Frontdoor-Views (grau)

Maximum Likelihood Uncertainty Estimation: Robustness to Outliers

  • We benchmark the robustness of maximum likelihood based uncertainty estimation methods to outliers in training data for regression tasks. Outliers or noisy labels in training data results in degraded performances as well as incorrect estimation of uncertainty. We propose the use of a heavy-tailed distribution (Laplace distribution) to improve the robustness to outliers. This property is evaluated using standard regression benchmarks and on a high-dimensional regression task of monocular depth estimation, both containing outliers. In particular, heavy-tailed distribution based maximum likelihood provides better uncertainty estimates, better separation in uncertainty for out-of-distribution data, as well as better detection of adversarial attacks in the presence of outliers.

Download full text files

Export metadata

Additional Services

Search Google Scholar Check availability


Show usage statistics
Document Type:Conference Object
Author:Deebul S. Nair, Nico Hochgeschwender, Miguel A. Olivares-Mendez
Number of pages:8
Publishing Institution:Hochschule Bonn-Rhein-Sieg
Date of first publication:2022/02/15
Publication status:The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), The AAAI's Workshop on Artificial Intelligence Safety
Copyright:Copyright © 2022, for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Funding:This work was supported by the European Union’s Horizon 2020 project SciRoc (grant agreement No 780086), SESAME (grant agreement No 101017258) and DLR CASSy project.
Departments, institutes and facilities:Fachbereich Informatik
Institut für Cyber Security & Privacy (ICSP)
Projects:SESAME Secure and Safe Multi-Robot Systems (EC/H2020/101017258)
SciRoc European Robotics League plus Smart Cities Robot Competitions (EC/H2020/780086)
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Entry in this database:2022/03/09
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International