Kasra Jalaldoust


kasra@cs.columbia.edu


CS@Columbia



Causal Discovery in Hawkes Processes by Minimum Description Length


AAAI2022 - Oral Presentation (<1%, out of 9020 papers)


Kasra Jalaldoust, Kateřina Hlaváčková-Schindler, Claudia Plant
Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, 2022 Jun, pp. 6978-6987


technical report
Cite

Cite

APA   Click to copy
Jalaldoust, K., Hlaváčková-Schindler, K., & Plant, C. (2022). Causal Discovery in Hawkes Processes by Minimum Description Length. Proceedings of the AAAI Conference on Artificial Intelligence, 36, 6978–6987. https://doi.org/10.1609/aaai.v36i6.20656


Chicago/Turabian   Click to copy
Jalaldoust, Kasra, Kateřina Hlaváčková-Schindler, and Claudia Plant. “Causal Discovery in Hawkes Processes by Minimum Description Length.” Proceedings of the AAAI Conference on Artificial Intelligence 36 (June 2022): 6978–6987.


MLA   Click to copy
Jalaldoust, Kasra, et al. “Causal Discovery in Hawkes Processes by Minimum Description Length.” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, June 2022, pp. 6978–87, doi:10.1609/aaai.v36i6.20656.


BibTeX   Click to copy

@article{jalaldoust2022a,
  title = {Causal Discovery in Hawkes Processes by Minimum Description Length},
  year = {2022},
  month = jun,
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  pages = {6978-6987},
  volume = {36},
  doi = {10.1609/aaai.v36i6.20656},
  author = {Jalaldoust, Kasra and Hlaváčková-Schindler, Kateřina and Plant, Claudia},
  month_numeric = {6}
}

Abstract

Hawkes processes are a special class of temporal point processes which exhibit a natural notion of causality, as occurrence of events in the past may increase the probability of events in the future. Discovery of the underlying influence network among the dimensions of multi-dimensional temporal processes is of high importance in disciplines where a high-frequency data is to model, e.g. in financial data or in seismological data. This paper approaches the problem of learning Granger-causal network in multi-dimensional Hawkes processes. We formulate this problem as a model selection task in which we follow the minimum description length (MDL) principle. Moreover, we propose a general algorithm for MDL-based inference using a Monte-Carlo method and we use it for our causal discovery problem. We compare our algorithm with the state-of-the-art baseline methods on synthetic and real-world financial data. The synthetic experiments demonstrate superiority of our method incausal graph discovery compared to the baseline methods with respect to the size of the data. The results of experiments with the G-7 bonds price data are consistent with the experts knowledge.