Causal Discovery in Hawkes Processes by Minimum Description Length

0569861 - ÚI 2023 RIV US eng C - Conference Paper (international conference)
Jalaldoust, A. - Hlaváčková-Schindler, Kateřina - Plant, C.
Causal Discovery in Hawkes Processes by Minimum Description Length.
Proceedings of the 36th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2022, s. 6978-6987. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36 No. 6: AAAI-22 Technical Tracks 6. ISBN 978-1-57735-876-3. ISSN 2159-5399. E-ISSN 2374-3468.
[The AAAI Conference on Artificial Intelligence /36./. Online (US), 22.02.2022-01.03.2022]
R&D Projects: GA ČR(CZ) GA19-16066S
Institutional support: RVO:67985807
Keywords : Granger causality * minimum description length principle * probability distributions * Hawkes process
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
https://ojs.aaai.org/index.php/AAAI/article/view/20656/20415

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 infuence 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 fnancial 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 fnancial data. The synthetic experiments demonstrate superiority of our method in causal 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.
Permanent Link: https://hdl.handle.net/11104/0341202