Learning Hawkes Processes from a Handful of Events

Learning the causal-interaction network of multivariate Hawkes processes is a useful task in many applications. Maximum-likelihood estimation is the most common approach to solve the problem in the presence of long observation sequences. However, when only short sequences are available, the lack of data amplifies the risk of overfitting and regularization becomes critical. Due to the challenges of hyper-parameter tuning, state-of-the-art methods only parameterize regularizers by a single shared hyper-parameter, hence limiting the power of representation of the model. To solve both issues, we develop in this work an efficient algorithm based on variational expectation-maximization. Our approach is able to optimize over an extended set of hyper-parameters. It is also able to take into account the uncertainty in the model parameters by learning a posterior distribution over them. Experimental results on both synthetic and real datasets show that our approach significantly outperforms state-of-the-art methods under short observation sequences.

Published in:
Proceedings of 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada.
Presented at:
33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, December 8-14, 2019
Appearing at NeurIPS 2019
Other identifiers:
Additional link:

Note: The status of this file is: Anyone

 Record created 2019-11-04, last modified 2020-07-14

Download fulltext

Rate this document:

Rate this document:
(Not yet reviewed)