Machine learning researcher at Veo Technologies. Previously at AWS (time series forecasting), Inria Sophia Antipolis, and DTU (Technical University of Denmark).
My research interests span probabilistic generative models, energy-based models, normalizing flows, missing data, and time series forecasting. I now work on sports video analysis and ML for sports.
-
Learning Energy-Based Models by Self-normalising the Likelihood H. Senetaire, P. Jeha, P.A. Mattei, J. Frellsen -- TMLR 2026 [paper]
-
ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables S.P. Arango, P. Mercado, S. Kapoor, A.F. Ansari, L. Stella, H. Shen, H. Senetaire, ... -- AISTATS 2025 [paper]
-
Explainability as Statistical Inference H.H.J. Senetaire, D. Garreau, J. Frellsen, P.A. Mattei -- ICML 2023 [paper]
-
Model-Agnostic Out-of-Distribution Detection Using Combined Statistical Tests F. Bergamin, P.A. Mattei, J.D. Havtorn, H. Senetaire, H. Schmutz, L. Maaløe, S. Hauberg, J. Frellsen -- AISTATS 2022 [paper]