Conformal Anomaly Detection for Functional Data with Elastic Distance Metrics

Jason Adams, Brandon Berman, Joshua Michalenko, J. Derek Tucker
Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 266:666-686, 2025.

Abstract

This paper considers the problem of outlier detection in functional data analysis with a particular focus on the more difficult case of shape outliers. We present an inductive conformal anomaly detection method based on elastic functional distance metrics. This method is evaluated and compared to similar conformal anomaly detection methods for functional data using simulation experiments. The method is also used in the analysis of a real exemplar data set that shows its utility in a practical application. The results demonstrate the efficacy of the proposed method for detecting both magnitude and shape outliers.

Cite this Paper

BibTeX
@InProceedings{pmlr-v266-adams25b, title = {Conformal Anomaly Detection for Functional Data with Elastic Distance Metrics}, author = {Adams, Jason and Berman, Brandon and Michalenko, Joshua and Tucker, J. Derek}, booktitle = {Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {666--686}, year = {2025}, editor = {Nguyen, Khuong An and Luo, Zhiyuan and Papadopoulos, Harris and Löfström, Tuwe and Carlsson, Lars and Boström, Henrik}, volume = {266}, series = {Proceedings of Machine Learning Research}, month = {10--12 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v266/main/assets/adams25b/adams25b.pdf}, url = {https://proceedings.mlr.press/v266/adams25b.html}, abstract = {This paper considers the problem of outlier detection in functional data analysis with a particular focus on the more difficult case of shape outliers. We present an inductive conformal anomaly detection method based on elastic functional distance metrics. This method is evaluated and compared to similar conformal anomaly detection methods for functional data using simulation experiments. The method is also used in the analysis of a real exemplar data set that shows its utility in a practical application. The results demonstrate the efficacy of the proposed method for detecting both magnitude and shape outliers.} }
Endnote
%0 Conference Paper %T Conformal Anomaly Detection for Functional Data with Elastic Distance Metrics %A Jason Adams %A Brandon Berman %A Joshua Michalenko %A J. Derek Tucker %B Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2025 %E Khuong An Nguyen %E Zhiyuan Luo %E Harris Papadopoulos %E Tuwe Löfström %E Lars Carlsson %E Henrik Boström %F pmlr-v266-adams25b %I PMLR %P 666--686 %U https://proceedings.mlr.press/v266/adams25b.html %V 266 %X This paper considers the problem of outlier detection in functional data analysis with a particular focus on the more difficult case of shape outliers. We present an inductive conformal anomaly detection method based on elastic functional distance metrics. This method is evaluated and compared to similar conformal anomaly detection methods for functional data using simulation experiments. The method is also used in the analysis of a real exemplar data set that shows its utility in a practical application. The results demonstrate the efficacy of the proposed method for detecting both magnitude and shape outliers.
APA
Adams, J., Berman, B., Michalenko, J. & Tucker, J.D.. (2025). Conformal Anomaly Detection for Functional Data with Elastic Distance Metrics. Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 266:666-686 Available from https://proceedings.mlr.press/v266/adams25b.html.

Related Material