Issue |
ESAIM: ProcS
Volume 80, 2025
Journées MAS 2022 - Dynamic and Stochastic Modelling
|
|
---|---|---|
Page(s) | 2 - 16 | |
DOI | https://doi.org/10.1051/proc/202580002 | |
Published online | 19 March 2025 |
Regularization techniques for inhomogeneous (spatial) point processes intensity and conditional intensity estimation*,**,***
1
Univ. Grenoble Alpes, LJK, 38000 Grenoble, France
2
Department of Mathematics and Statistics, York University, Toronto, Ontario, Canada
3
Department of Statistics, Institut Teknologi Sepuluh Nopember, 60111 Surabaya, Indonesia
Point processes are stochastic models generating interacting points or events in time and/or space. Among characteristics of these models, first-order intensity and conditional intensity functions are often considered. We focus on inhomogeneous parametric forms of these functions assumed to depend on a certain number of spatial covariates. When this number of covariates is large, we are faced with a high-dimensional problem. This paper provides an overview of these questions and existing solutions based on regularizations.
Résumé
Les processus ponctuels constituent une classe de modèles stochastiques permettant de modéliser des évènements dans le temps et/ou l’espace en interaction. Parmi les caractéristiques d’un processus ponctuel, l’intensitéet l’intensitéconditionnelle d’ordre un sont souvent considérées. Nous nous concentrons ici sur des formes paramétriques inhomogènes de ces fonctions que nous supposons dépendre d’un certain nombre de covariables spatiales. Lorsque ce nombre est élevé, nous faisons face à un problème de grande dimension. Ce papier a pour objectif de présenter un aperçu de ces problèmes et solutions existantes.
© EDP Sciences, SMAI 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.