论文信息 - AN EM ALGORITHM FOR HAWKES PROCESS

AN EM ALGORITHM FOR HAWKES PROCESS

This manuscript addresses the EM algorithm developed in Halpin & De Boeck (in press). The runtime of the algorithm grows quadratically in the number of observations, making its application to large data sets impractical. A strategy for improving efficiency is introduced, and this results in linear growth for many applications. The performance of the modified algorithm is assessed using data simulation.

Peter F. Halpin | Peter F Halpin

[1] Yosihiko Ogata,et al. Statistical Models for Earthquake Occurrences and Residual Analysis for Point Processes , 1988 .

[2] R. M. Loynes,et al. Non-Linear Regression. , 1990 .

[3] Daryl J. Daley,et al. An Introduction to the Theory of Point Processes , 2013 .

[4] Geoffrey J. McLachlan,et al. Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.

[5] Albert-László Barabási,et al. The origin of bursts and heavy tails in human dynamics , 2005, Nature.

[6] Uri T Eden,et al. A point process framework for relating neural spiking activity to spiking history, neural ensemble, and extrinsic covariate effects. , 2005, Journal of neurophysiology.

[7] A. Veen,et al. Estimation of Space–Time Branching Process Models in Seismology Using an EM–Type Algorithm , 2006 .

[8] Didier Sornette,et al. Robust dynamic classes revealed by measuring the response function of a social system , 2008, Proceedings of the National Academy of Sciences.

[9] J. Rasmussen. Bayesian Inference for Hawkes Processes , 2013 .