Welcome to my homepage!
I am an associate researcher (chargé de recherche) at Inria Grenoble - Rhône-Alpes in the Statify team and member of Laboratoire Jean Kuntzmann in Université Grenoble Alpes. Prior to that, I was a postdoc at Bocconi University (Milan) and Collegio Carlo Alberto (Turin), and a statistician at Insee (French National Institute of Statistics and Economic Studies, Paris). I received my PhD in Applied Mathematics (Statistics) at Université Paris-Dauphine (with Judith Rousseau and Ghislaine Gayraud). I graduated from Ecole Polytechnique and ENSAE. I defended the French HDR in 2019. I am writing on the collaborative blog Statisfaction (formerly hosted here). More in my CV.
I strive to fly less.
Bayesian Statistics: Approximations; Computation; Nonparametrics; Extreme value theory; Objective Bayes.
Bayesian Machine Learning: Bayesian neural networks; Variational inference.
Applications of the above in Environmental science, Neuroscience.
Bayesian Analysis (2019- )
Statistics & Probability Letters (2019- )
[30 Oct. - 3 Nov.] Bayesian autumn school, CIRM, Marseille.
[Oct 2] Talk at the University of Edinburgh, about "Rapture of the deep: highs and lows of Bayes in a world of depths"
[Sept] "A Primer on Bayesian Neural Networks: Review and Debates" on arXiv.
[November] We have launched a Bayesian Group at the French stat society (SFdS).
[October] I submitted my first review for COMPUTO, the new journal of the French stat society (SFdS).
[October] I'm a Management Committee Member of the HiTEc COST Action.
[March 30] I was part of the PhD jury of Meryem Bousebata: "Statistical inference for extreme risk measures: Implication for the insurance of natural disasters."
[March 23] I was part of the PhD jury of Ioanni Mitro: "Bayesian Neural Networks for Out of Distribution Detection".
[March 22] Mariia Vladimirova defended her PhD entitled "Distributional Properties of Bayesian Neural Networks".
[Nov 27] Talk at Oaxaca OBayes workshop on Extreme value theory with noninformative priors & MCMC convergence diagnostic with a local R-hat. Video.
[Sept] Paper accepted at ACML: Bayesian neural network unit priors and generalized Weibull-tail property.
[Sept] New preprint: Approximate Bayesian computation with surrogate posteriors.
[May] Paper accepted at ANZJS: BNPdensity: Bayesian nonparametric mixture modeling in R. Link to R package.
Phone: (+33) 6 43 28 75 03
Office: Inria Grenoble Rhône-Alpes, 655 Avenue de l'Europe, 38330 Montbonnot-Saint-Martin, France.