New variational approach uses Wasserstein-Fisher-Rao geometry for Hawkes process intensity estimation

Researchers have developed a new variational approach for estimating the background intensity of a Hawkes process, particularly when the triggering mechanism is known but the background density is not. This method utilizes the Wasserstein-Fisher-Rao geometry and a distributional framework to handle dynamics that fall outside classical gradient-flow formulations. The approach involves projecting these dynamics onto statistical manifolds to derive a finite-dimensional scheme, with a focus on Gaussian-mixture manifolds for practical application. AI

IMPACT Introduces a novel statistical method for intensity estimation in point processes, potentially applicable in areas like anomaly detection or event forecasting.

RANK_REASON The cluster contains an academic paper detailing a new statistical method. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• Arturo Jaramillo
• arXiv
• Gaussian-mixture manifolds
• Hawkes process
• Wasserstein-Fisher-Rao

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →