The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM

Ardavan Saeedi, Matthew Hoffman, Matthew Johnson, Ryan Adams
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:2682-2691, 2016.

Abstract

We propose the segmented iHMM (siHMM), a hierarchical infinite hidden Markov model (iHMM) that supports a simple, efficient inference scheme. The siHMM is well suited to segmentation problems, where the goal is to identify points at which a time series transitions from one relatively stable regime to a new regime. Conventional iHMMs often struggle with such problems, since they have no mechanism for distinguishing between high-and low-level dynamics. Hierarchical HMMs (HHMMs) can do better, but they require much more complex and expensive inference algorithms. The siHMM retains the simplicity and efficiency of the iHMM, but outperforms it on a variety of segmentation problems, achieving performance that matches or exceeds that of a more complicated HHMM.

Cite this Paper

BibTeX
@InProceedings{pmlr-v48-saeedi16, title = {The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM}, author = {Saeedi, Ardavan and Hoffman, Matthew and Johnson, Matthew and Adams, Ryan}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {2682--2691}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/saeedi16.pdf}, url = {https://proceedings.mlr.press/v48/saeedi16.html}, abstract = {We propose the segmented iHMM (siHMM), a hierarchical infinite hidden Markov model (iHMM) that supports a simple, efficient inference scheme. The siHMM is well suited to segmentation problems, where the goal is to identify points at which a time series transitions from one relatively stable regime to a new regime. Conventional iHMMs often struggle with such problems, since they have no mechanism for distinguishing between high-and low-level dynamics. Hierarchical HMMs (HHMMs) can do better, but they require much more complex and expensive inference algorithms. The siHMM retains the simplicity and efficiency of the iHMM, but outperforms it on a variety of segmentation problems, achieving performance that matches or exceeds that of a more complicated HHMM.} }
Endnote
%0 Conference Paper %T The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM %A Ardavan Saeedi %A Matthew Hoffman %A Matthew Johnson %A Ryan Adams %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-saeedi16 %I PMLR %P 2682--2691 %U https://proceedings.mlr.press/v48/saeedi16.html %V 48 %X We propose the segmented iHMM (siHMM), a hierarchical infinite hidden Markov model (iHMM) that supports a simple, efficient inference scheme. The siHMM is well suited to segmentation problems, where the goal is to identify points at which a time series transitions from one relatively stable regime to a new regime. Conventional iHMMs often struggle with such problems, since they have no mechanism for distinguishing between high-and low-level dynamics. Hierarchical HMMs (HHMMs) can do better, but they require much more complex and expensive inference algorithms. The siHMM retains the simplicity and efficiency of the iHMM, but outperforms it on a variety of segmentation problems, achieving performance that matches or exceeds that of a more complicated HHMM.
RIS
TY - CPAPER TI - The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM AU - Ardavan Saeedi AU - Matthew Hoffman AU - Matthew Johnson AU - Ryan Adams BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-saeedi16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 2682 EP - 2691 L1 - http://proceedings.mlr.press/v48/saeedi16.pdf UR - https://proceedings.mlr.press/v48/saeedi16.html AB - We propose the segmented iHMM (siHMM), a hierarchical infinite hidden Markov model (iHMM) that supports a simple, efficient inference scheme. The siHMM is well suited to segmentation problems, where the goal is to identify points at which a time series transitions from one relatively stable regime to a new regime. Conventional iHMMs often struggle with such problems, since they have no mechanism for distinguishing between high-and low-level dynamics. Hierarchical HMMs (HHMMs) can do better, but they require much more complex and expensive inference algorithms. The siHMM retains the simplicity and efficiency of the iHMM, but outperforms it on a variety of segmentation problems, achieving performance that matches or exceeds that of a more complicated HHMM. ER -
APA
Saeedi, A., Hoffman, M., Johnson, M. & Adams, R.. (2016). The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:2682-2691 Available from https://proceedings.mlr.press/v48/saeedi16.html.

Related Material