PhD student at CERMICS (Ecole Nationale des Ponts et Chaussées) under the supervision of Gabriel Stoltz.
My focus is on the understanding of statistical physics and random systems from a mathematical perspective, both concerning theoretical and practical aspects. To be more specific, my PhD is concerned with designing efficient algorithms for sampling rare events probabilities in random systems, such as Feynman-Kac dynamics or adaptive algorithms. I have also been involved in a Machine Learning project for statistical physics in collaboration with the French Nuclear Agency and the Los Alamos National Laboratory, and I am still interested in the links between statistical physics, high dimensional sampling and Machine Learning.
- Markov chains, Feynman-Kac models and their stability;
- Large deviations theory and its application to physics (phase transition...);
- Interaction between Machine Learning and statistical physics;
- Numerical analysis of SDE's;
- Stochastic algorithms (MCMC, stochastic approximation, sequential Monte Carlo...);
- Partial differential equations, functional inequalities.
Ferré, G. , Rousset, M. & Stoltz, G., More on the stability of Feynman-Kac semigroups. Preprint
Chafaï, D. & Ferré, G. (2018), Simulating Coulomb gases and log-gases with Hybrid Monte Carlo algorithms. Preprint
Ferré, G. & Touchette, H. (2018). Adaptive sampling of large deviations. The Journal of Statistical Physics, July 4th 2018. Preprint
Ferré, G, & Stoltz, G. (2017). Error estimates on ergodic properties of Feynman-Kac semigroups. Preprint
Machine Learning and model reduction
Ferré, G., Haut, T., & Barros, K. (2017). Learning molecular energies using localized graph kernels. The Journal of Chemical Physics, 146(11), 114107. Preprint
Zentner, I., Ferré, G., Poirion, F., & Benoit, M. (2016). A biorthogonal decomposition for the identification and simulation of non-stationary and non-Gaussian random fields. Journal of Computational Physics, 314, 1-13. Paper
Ferré, G., Maillet, J. B., & Stoltz, G. (2015). Permutation-invariant distance between atomic configurations. The Journal of Chemical Physics, 143(10), 104114. Preprint
Institute for Pure and Applied Mathematics, UCLA, Los Angeles, Understanding Many-Particle Systems with Machine Learning, 2016, Young Researchers’ Talk. Learning potential energy landscapes with localized graph kernels. Slides
ICTS, Bengalore, Large deviations theory in statistical physics, recent advances and future challenges, 2017, Error estimates for Feynman-Kac semi-groups. Video
IHP, Paris, Young Probabilists' Day (Les probabilités de demain), 2018, Long time stability of Feynman-Kac models. Slides Video
Congrès National d'Analyse Numérique, Cap d'Agde, Error estimates and ergodic properties of Markov chains and Feynman-Kac models, 2018.
International Conference in Monte Carlo and Quasi-Monte Carlo Methods in Scientific computing, Rennes, Long time stability of Feynman-Kac dynamics, 2018. Slides
SIAM meeting on Mathematical Aspects of Material Science, Portland (Oregon), Error Estimates and Stability for Diffusion Monte Carlo Algorithms, 2018.
SIAM meeting on Mathematical Aspects of Material Science, Portland (Oregon), An Adaptive Algorithm for Sampling Large Deviation Functions, 2018.
Franco-German Meeting Workshop on Mathematical Aspects in Computational Chemistry, Aachen, Feynman-Kac models: stability and further issues, 2018.
IHP, Paris, Stochastic Dynamics Out of Equilibrium, 2017, Young Researchers’ Seminar. Error estimates for Feynman-Kac semi-groups. Slides
CERMICS, ENPC, PhD seminar, 2018, Crash course on ergodicity for Markov chains: doing probabilities like an analyst.
IPAM, Los Angeles, Understanding Many-Particle Systems with Machine Learning, 2016.
IHP, Paris, Stochastic Dynamics Out of Equilibrium, 2017.
IPAM, Los Angeles, Complex High-Dimensional Energy Landscapes, 2017.
Duke University, Durham, Quasi Monte-Carlo and High-Dimensional Sampling Methods for Applied Mathematics, 2017.
Alan Turing Institute, London, Data-Driven Modelling of Complex Systems, 2018.
INRIA Rennes, Simulation aléatoire : problèmes actuels, 2018.
Participation to workshops
CIRM, Marseille, Stochastic dynamics out of equilibrium, April 2017.
YES'X Workshop, Eindhoven, Scalable statistics: Accuracy and computational complexity, March 2018.
INRIA Rennes, Simulation aléatoire : problèmes actuels, May 2018.
University of Cambridge, Cambridge (UK), Department of engineering, with G. Csanyi, July 2015 (two weeks).
Los Alamos National Laboratory, US, Center for Nonlinear Studies, with K. Barros, summer 2016 (three months).
UCLA, Los Angeles, IPAM Long Program: Understanding Many-Particle Systems with Machine Learning, fall 2016 (two months).
ICTS, Bengalore, Large deviations theory in statistical physics, recent advances and future challenges, summer 2017 (two weeks).
Analysis, 1st year undergraduates (differenciation, optimization...) , University Paris Dauphine, 2017.
Tutorship for analysis, 1st year at Ecole des Ponts (Sobolev spaces, distributions, Dirichlet problem...), 2017.
Project of 4 students at Ecole des Ponts, Branching algorithms for computing eigenvalues of operators, 2018.
Mentoring of a graduate-level six month internship, Stein Variational Gradient Descent algorithm, 2018.
Intensive course in analysis (differential calculus and measure theory) for first year students at Ecole des Ponts (10 hours, three days), 2018.
Co-organizer of a one-year working group (2017-2018) in statistical physics and related fields (J-PSI), including a final event gathering about 30 participants on June 19th, 2018. See the web page of the group here.
Member (elected) of the comity of Ponts Alumni.