Variational Inference for Gaussian Processes with Panel Count Data

Hongyi Ding, Young Lee, Issei Sato, Masashi Sugiyama
Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, PMLR R16:289-298, 2018.

Abstract

We present the first framework for Gaussian- process-modulated Poisson processes when the temporal data appear in the form of panel counts. Panel count data frequently arise when experimental subjects are observed only at dis- crete time points and only the numbers of oc- currences of the events between subsequent observation times are available. The exact occurrence timestamps of the events are un- known. The method of conducting the efficient variational inference is presented, based on the assumption of a Gaussian-process-modulated intensity function. We derive a tractable lower bound to alleviate the problems of the in- tractable evidence lower bound inherent in the variational inference framework. Our algo- rithm outperforms classical methods on both synthetic and three real panel count sets.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR16-ding18a, title = {Variational Inference for {G}aussian Processes with Panel Count Data}, author = {Ding, Hongyi and Lee, Young and Sato, Issei and Sugiyama, Masashi}, booktitle = {Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence}, pages = {289--298}, year = {2018}, editor = {Globerson, Amir and Silva, Ricardo}, volume = {R16}, series = {Proceedings of Machine Learning Research}, month = {06--10 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r16/main/assets/ding18a/ding18a.pdf}, url = {https://proceedings.mlr.press/r16/ding18a.html}, abstract = {We present the first framework for Gaussian- process-modulated Poisson processes when the temporal data appear in the form of panel counts. Panel count data frequently arise when experimental subjects are observed only at dis- crete time points and only the numbers of oc- currences of the events between subsequent observation times are available. The exact occurrence timestamps of the events are un- known. The method of conducting the efficient variational inference is presented, based on the assumption of a Gaussian-process-modulated intensity function. We derive a tractable lower bound to alleviate the problems of the in- tractable evidence lower bound inherent in the variational inference framework. Our algo- rithm outperforms classical methods on both synthetic and three real panel count sets.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Variational Inference for Gaussian Processes with Panel Count Data %A Hongyi Ding %A Young Lee %A Issei Sato %A Masashi Sugiyama %B Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2018 %E Amir Globerson %E Ricardo Silva %F pmlr-vR16-ding18a %I PMLR %P 289--298 %U https://proceedings.mlr.press/r16/ding18a.html %V R16 %X We present the first framework for Gaussian- process-modulated Poisson processes when the temporal data appear in the form of panel counts. Panel count data frequently arise when experimental subjects are observed only at dis- crete time points and only the numbers of oc- currences of the events between subsequent observation times are available. The exact occurrence timestamps of the events are un- known. The method of conducting the efficient variational inference is presented, based on the assumption of a Gaussian-process-modulated intensity function. We derive a tractable lower bound to alleviate the problems of the in- tractable evidence lower bound inherent in the variational inference framework. Our algo- rithm outperforms classical methods on both synthetic and three real panel count sets. %Z Reissued by PMLR on 04 October 2026.
APA
Ding, H., Lee, Y., Sato, I. & Sugiyama, M.. (2018). Variational Inference for Gaussian Processes with Panel Count Data. Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R16:289-298 Available from https://proceedings.mlr.press/r16/ding18a.html. Reissued by PMLR on 04 October 2026.

Related Material