Skip to content

Latest commit

 

History

History
50 lines (50 loc) · 2.03 KB

2024-04-18-augusto-zagatti24a.md

File metadata and controls

50 lines (50 loc) · 2.03 KB
title software abstract layout series publisher issn id month tex_title firstpage lastpage page order cycles bibtex_author author date address container-title volume genre issued pdf extras
Learning multivariate temporal point processes via the time-change theorem
Marked temporal point processes (TPPs) are a class of stochastic processes that describe the occurrence of a countable number of marked events over continuous time. In machine learning, the most common representation of marked TPPs is the univariate TPP coupled with a conditional mark distribution. Alternatively, we can represent marked TPPs as a multivariate temporal point process in which we model each sequence of marks interdependently. We introduce a learning framework for multivariate TPPs leveraging recent progress on learning univariate TPPs via time-change theorems to propose a deep-learning, invertible model for the conditional intensity. We rely neither on Monte Carlo approximation for the compensator nor on thinning for sampling. Therefore, we have a generative model that can efficiently sample the next event given a history of past events. Our models show strong alignment between the percentiles of the distribution expected from theory and the empirical ones.
inproceedings
Proceedings of Machine Learning Research
PMLR
2640-3498
augusto-zagatti24a
0
Learning multivariate temporal point processes via the time-change theorem
3241
3249
3241-3249
3241
false
Augusto Zagatti, Guilherme and Kiong Ng, See and Bressan, St\'{e}phane
given family
Guilherme
Augusto Zagatti
given family
See
Kiong Ng
given family
Stéphane
Bressan
2024-04-18
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics
238
inproceedings
date-parts
2024
4
18