Sébastien Marmin’s research focuses on probabilistic methods for machine learning, combining uncertainty quantification, deep probabilistic models, Bayesian inference and optimal design for computer experiments, with real-world applications in computer experiments, live sciences, image analysis and mechanical engineering.

He obtained his PhD in January 2018 from the Bern mathematical statistics group, jointly with Centrale Marseille and funded by the National Expert Service in Nuclear Safety. Prior to that he studied engineering at Mines Saint-Étienne in a double degree program (Master’s degree in Applied Mathematics).

He teaches Gaussian Process models in Prof Maurizio Filippone’s course on Advanced Statistical Inference and supervises student projects in data science.