Théophile Cantelobre

PhD Candidate @ SIERRA Team (Inria Paris & Inria London Programme)

first.last@inria.fr

I am interested in using kernel methods to solve machine learning problems in an efficient way, with a particular interest for geometrical and constrained data.

I am a PhD candidate in Computer Science based in the SIERRA project-team (Inria Paris DI-ENS) and in the Inria London Programme, supervised by Alessandro Rudi and Benjamin Guedj.

Before my PhD, I studied Mathematics & Engineering in a dual masters program between Mines ParisTech (Cycle Ingénieur Civil) and Sorbonne Université (M2A) in Paris, France.

In the past, I worked on PAC-Bayes guarantess for structured prediction at Inria & UCL, and state estimation for underwater robotics at Schlumberger-Doll Research.

Learn more in my CV…

news

Jul 17, 2022 Presenting our work at ICML2022 in Baltimore.
Oct 1, 2021 Started my PhD @ Inria between Paris and London!
Dec 7, 2020 New preprint with Benjamin Guedj, María Pérez-Ortiz, and John-Shawe Taylor is online.
Oct 25, 2020 IROS 2020 is open for free to everyone, come check out our work!

publications

  1. Measuring dissimilarity with diffeomorphism invariance
    Théophile Cantelobre, Carlo Ciliberto, Benjamin Guedj, and Alessandro Rudi
    In Proceedings of the 39th International Conference on Machine Learning 2022
  2. A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings
    arXiv 2012.03780, 2020
  3. A real-time unscented Kalman filter on manifolds for challenging AUV navigation
    Théophile Cantelobre, Clément Chahbazian, Arnaud Croux, and Silvère Bonnabel
    In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2020