Seminar Cascading Extremes and Generative AI Modeling of Extreme Events
9 April 2026
Seminar of the “STAT Research Seminars 2026” series organized by the Department of Statistical Sciences “Paolo Fortunati”.
- 02:30 PM - 03:30 PM
- Online on Microsoft Teams and in person : Aula Seminari, Dipartimento di Scienze Statistiche, Via Belle Arti 41, Bologna
- Training, Science & Technology In English
How to partecipate
Free admission
Program
Speaker: Miguel de Carvalho (University of Edinburgh)
Abstract:
In this talk, I first motivate the notion of cascades of extremes—as recently introduced by de Carvalho, Ferrer & Vallejos (2026, Extremes)—such as a tsunami followed by an earthquake or a cascade of stock market losses. I will introduce the notion of POC (Probability of Cascade) surface, and will develop a neural model based on the Kolmogorov superposition theorem to learn about it from data. I then argue that the sequential nature of cascading extremes makes them particularly appealing for the setting of generative extremes, and introduce an generative framework grounded on extreme value theory that synthesizes cascades through causal attention. Simulated and real data examples will be used to illustrate the scope of the proposed approaches.
Organizer: Luca Trapin