Detecting Change-Points in Time Series by Maximum Mean Discrepancy of Ordinal Pattern Distributions

Mathieu Sinn, Ali Ghodsi, Karsten Keller
Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, PMLR R10:785-793, 2012.

Abstract

As a new method for detecting change-points in high-resolution time series, we apply Maximum Mean Discrepancy to the distributions of ordinal patterns in different parts of a time series. The main advantage of this approach is its computational simplicity and robustness with respect to (non-linear) monotonic transformations, which makes it particularly well-suited for the analysis of long biophysical time series where the exact calibration of measurement devices is unknown or varies with time. We establish consistency of the method and evaluate its performance in simulation studies. Furthermore, we demonstrate the application to the analysis of electroencephalography (EEG) and electrocardiography (ECG) recordings.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR10-sinn12a, title = {Detecting Change-Points in Time Series by Maximum Mean Discrepancy of Ordinal Pattern Distributions}, author = {Sinn, Mathieu and Ghodsi, Ali and Keller, Karsten}, booktitle = {Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence}, pages = {785--793}, year = {2012}, editor = {de Freitas, Nando and Murphy, Kevin}, volume = {R10}, series = {Proceedings of Machine Learning Research}, month = {14--18 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r10/main/assets/sinn12a/sinn12a.pdf}, url = {https://proceedings.mlr.press/r10/sinn12a.html}, abstract = {As a new method for detecting change-points in high-resolution time series, we apply Maximum Mean Discrepancy to the distributions of ordinal patterns in different parts of a time series. The main advantage of this approach is its computational simplicity and robustness with respect to (non-linear) monotonic transformations, which makes it particularly well-suited for the analysis of long biophysical time series where the exact calibration of measurement devices is unknown or varies with time. We establish consistency of the method and evaluate its performance in simulation studies. Furthermore, we demonstrate the application to the analysis of electroencephalography (EEG) and electrocardiography (ECG) recordings.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Detecting Change-Points in Time Series by Maximum Mean Discrepancy of Ordinal Pattern Distributions %A Mathieu Sinn %A Ali Ghodsi %A Karsten Keller %B Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2012 %E Nando de Freitas %E Kevin Murphy %F pmlr-vR10-sinn12a %I PMLR %P 785--793 %U https://proceedings.mlr.press/r10/sinn12a.html %V R10 %X As a new method for detecting change-points in high-resolution time series, we apply Maximum Mean Discrepancy to the distributions of ordinal patterns in different parts of a time series. The main advantage of this approach is its computational simplicity and robustness with respect to (non-linear) monotonic transformations, which makes it particularly well-suited for the analysis of long biophysical time series where the exact calibration of measurement devices is unknown or varies with time. We establish consistency of the method and evaluate its performance in simulation studies. Furthermore, we demonstrate the application to the analysis of electroencephalography (EEG) and electrocardiography (ECG) recordings. %Z Reissued by PMLR on 04 October 2026.
APA
Sinn, M., Ghodsi, A. & Keller, K.. (2012). Detecting Change-Points in Time Series by Maximum Mean Discrepancy of Ordinal Pattern Distributions. Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R10:785-793 Available from https://proceedings.mlr.press/r10/sinn12a.html. Reissued by PMLR on 04 October 2026.

Related Material