Mesochronal Structure Learning

Sergey Plis, Jianyu Yang, David Danks Carnegie Mellon University
Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, PMLR R13:890-899, 2015.

Abstract

Standard time series structure learning algorithms assume that the measurement timescale is approximately the same as the timescale of the underlying (causal) system. In many scientific contexts, however, this assumption is violated: the measurement timescale can be substantially slower than the system timescale (i.e., many intermediate time series datapoints are missing). This assumption violation can lead to significant learning errors. In this paper, we provide a novel learning algorithm that can extract system-timescale structure given measurement data that undersample the underlying system. Substantial algorithmic optimizations were required to achieve computational tractability. We conclude by showing that the algorithm is highly reliable at extracting system-timescale structure from undersampled data.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR13-plis15a, title = {Mesochronal Structure Learning}, author = {Plis, Sergey and Yang, Jianyu and University, David Danks Carnegie Mellon}, booktitle = {Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence}, pages = {890--899}, year = {2015}, editor = {Meila, Marina and Heskes, Tom}, volume = {R13}, series = {Proceedings of Machine Learning Research}, month = {12--16 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r13/main/assets/plis15a/plis15a.pdf}, url = {https://proceedings.mlr.press/r13/plis15a.html}, abstract = {Standard time series structure learning algorithms assume that the measurement timescale is approximately the same as the timescale of the underlying (causal) system. In many scientific contexts, however, this assumption is violated: the measurement timescale can be substantially slower than the system timescale (i.e., many intermediate time series datapoints are missing). This assumption violation can lead to significant learning errors. In this paper, we provide a novel learning algorithm that can extract system-timescale structure given measurement data that undersample the underlying system. Substantial algorithmic optimizations were required to achieve computational tractability. We conclude by showing that the algorithm is highly reliable at extracting system-timescale structure from undersampled data.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Mesochronal Structure Learning %A Sergey Plis %A Jianyu Yang %A David Danks Carnegie Mellon University %B Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2015 %E Marina Meila %E Tom Heskes %F pmlr-vR13-plis15a %I PMLR %P 890--899 %U https://proceedings.mlr.press/r13/plis15a.html %V R13 %X Standard time series structure learning algorithms assume that the measurement timescale is approximately the same as the timescale of the underlying (causal) system. In many scientific contexts, however, this assumption is violated: the measurement timescale can be substantially slower than the system timescale (i.e., many intermediate time series datapoints are missing). This assumption violation can lead to significant learning errors. In this paper, we provide a novel learning algorithm that can extract system-timescale structure given measurement data that undersample the underlying system. Substantial algorithmic optimizations were required to achieve computational tractability. We conclude by showing that the algorithm is highly reliable at extracting system-timescale structure from undersampled data. %Z Reissued by PMLR on 04 October 2026.
APA
Plis, S., Yang, J. & University, D.D.C.M.. (2015). Mesochronal Structure Learning. Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R13:890-899 Available from https://proceedings.mlr.press/r13/plis15a.html. Reissued by PMLR on 04 October 2026.

Related Material