Pierre-Alexandre Mattei
Generative Modeling Summer School (GeMSS)
R-miss-tastic
Since October 2021, I am a Postdoctoral researcher of the 3iA Côte d’Azur at Centre Inria d’Université Côte d’Azur in the Maasai team. I am now working on semi-supervised learning, with Charles Bouveyron and Pierre-Alexandre Mattei.
My PhD thesis (2018-2021) in Applied Mathematics was supervised by Claire Boyer and Julie Josse at Ecole Polytechnique (CMAP) and University Pierre and Marie Curie (LPSM). See dissertation , slides .
The goal of this PhD thesis was to propose new statistical methods to handle missing values in several supervised and unsupervised machine learning scenarios, particularly when the data can be Missing Not At Random (MNAR), i.e. when the unavailability of values depends on the missing values themselves and values of other variables. We have considered low-rank models (fixed and PPCA), online linear regression using SGD and model-based clustering.
Pierre-Alexandre Mattei
Generative Modeling Summer School (GeMSS)
R-miss-tastic