Current position :

I am currently an assistant professeur at the National School of Statistics and Information Analysis (ENSAI), IT department, member of the Center for Research in Economics and Statistics (CREST). I started my PhD thesis in 2013 at the University of Lille (Ecole centrale), CRIStAL laboratory, with Pierre Chainais. And I defended my thesis in 2016. During my thesis, I was also a member of the ANR-BNPSI project.

Research interests :

I am interested in Bayesian nonparametric approaches to machine learning. These models rely on stochastic processes such as the Dirichet process, the Chinese restaurant process or the Indian buffet process. The interest of these models is that the number of degrees of freedom of the model does not need to fix in advance. The result is models that get richer when the number of observations increases. In terms of applications, I am interested in image processing (segmentation, denoising, deconvolution or inpainting) and compressed sensing.

Keywords : machine learning, clustering, dictionary learning, matrix factorization, Bayesian non-parametric, stochastic process, Markov chain Monte Carlo,sparse representations, inverse problems, statistical signal processing, interaction between Bayesian methods and optimization.

Liens