Pierre Gaillard

---

I am a researcher (CRCN) at Inria, member of the THOTH team — a joint team of Inria Grenoble – Rhône-Alpes and the Laboratoire Jean Kuntzmann.

My research focuses on statistical learning theory, with a particular emphasis on online learning: sequential prediction and aggregation of experts, bandit problems (stochastic, adversarial, sleeping, dueling), online convex optimisation, and nonparametric regression. I also work on applications to reinforcement learning and demand forecasting, and I develop the Opera R package for online prediction by expert aggregation.

Success is the ability to go from one failure to another with no loss of enthusiasm.

Winston Churchill

Il suffit de regarder une chose avec attention pour qu’elle devienne intéressante.

Eugenio d’Ors Y Rovira