Modeling Correlated Arrival Events with Latent Semi-Markov Processes

Wenzhao Lian, Vinayak Rao, Brian Eriksson, Lawrence Carin
Proceedings of the 31st International Conference on Machine Learning, PMLR 32(1):396-404, 2014.

Abstract

The analysis and characterization of correlated point process data has wide applications, ranging from biomedical research to network analysis. In this work, we model such data as generated by a latent collection of continuous-time binary semi-Markov processes, corresponding to external events appearing and disappearing. A continuous-time modeling framework is more appropriate for multichannel point process data than a binning approach requiring time discretization, and we show connections between our model and recent ideas from the discrete-time literature. We describe an efficient MCMC algorithm for posterior inference, and apply our ideas to both synthetic data and a real-world biometrics application.

Cite this Paper

BibTeX
@InProceedings{pmlr-v32-lian14, title = {Modeling Correlated Arrival Events with Latent Semi-Markov Processes}, author = {Lian, Wenzhao and Rao, Vinayak and Eriksson, Brian and Carin, Lawrence}, booktitle = {Proceedings of the 31st International Conference on Machine Learning}, pages = {396--404}, year = {2014}, editor = {Xing, Eric P. and Jebara, Tony}, volume = {32}, number = {1}, series = {Proceedings of Machine Learning Research}, address = {Bejing, China}, month = {22--24 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v32/lian14.pdf}, url = {https://proceedings.mlr.press/v32/lian14.html}, abstract = {The analysis and characterization of correlated point process data has wide applications, ranging from biomedical research to network analysis. In this work, we model such data as generated by a latent collection of continuous-time binary semi-Markov processes, corresponding to external events appearing and disappearing. A continuous-time modeling framework is more appropriate for multichannel point process data than a binning approach requiring time discretization, and we show connections between our model and recent ideas from the discrete-time literature. We describe an efficient MCMC algorithm for posterior inference, and apply our ideas to both synthetic data and a real-world biometrics application.} }
Endnote
%0 Conference Paper %T Modeling Correlated Arrival Events with Latent Semi-Markov Processes %A Wenzhao Lian %A Vinayak Rao %A Brian Eriksson %A Lawrence Carin %B Proceedings of the 31st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2014 %E Eric P. Xing %E Tony Jebara %F pmlr-v32-lian14 %I PMLR %P 396--404 %U https://proceedings.mlr.press/v32/lian14.html %V 32 %N 1 %X The analysis and characterization of correlated point process data has wide applications, ranging from biomedical research to network analysis. In this work, we model such data as generated by a latent collection of continuous-time binary semi-Markov processes, corresponding to external events appearing and disappearing. A continuous-time modeling framework is more appropriate for multichannel point process data than a binning approach requiring time discretization, and we show connections between our model and recent ideas from the discrete-time literature. We describe an efficient MCMC algorithm for posterior inference, and apply our ideas to both synthetic data and a real-world biometrics application.
RIS
TY - CPAPER TI - Modeling Correlated Arrival Events with Latent Semi-Markov Processes AU - Wenzhao Lian AU - Vinayak Rao AU - Brian Eriksson AU - Lawrence Carin BT - Proceedings of the 31st International Conference on Machine Learning DA - 2014/01/27 ED - Eric P. Xing ED - Tony Jebara ID - pmlr-v32-lian14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 32 IS - 1 SP - 396 EP - 404 L1 - http://proceedings.mlr.press/v32/lian14.pdf UR - https://proceedings.mlr.press/v32/lian14.html AB - The analysis and characterization of correlated point process data has wide applications, ranging from biomedical research to network analysis. In this work, we model such data as generated by a latent collection of continuous-time binary semi-Markov processes, corresponding to external events appearing and disappearing. A continuous-time modeling framework is more appropriate for multichannel point process data than a binning approach requiring time discretization, and we show connections between our model and recent ideas from the discrete-time literature. We describe an efficient MCMC algorithm for posterior inference, and apply our ideas to both synthetic data and a real-world biometrics application. ER -
APA
Lian, W., Rao, V., Eriksson, B. & Carin, L.. (2014). Modeling Correlated Arrival Events with Latent Semi-Markov Processes. Proceedings of the 31st International Conference on Machine Learning, in Proceedings of Machine Learning Research 32(1):396-404 Available from https://proceedings.mlr.press/v32/lian14.html.

Related Material