Scholar
Pierre-Alexandre Mattei
Google Scholar ID: Tqa_-D0AAAAJ
Research scientist, Inria, Université Côte d'Azur
Citations & Impact
Citations
1,043
H-index
13
i10-index
16
Publications
20
Co-authors
11
list available
Contact
Publications
Resume (English only)
Academic Achievements
- He has published several preprints, including 'Parsimonious Gaussian mixture models with piecewise-constant eigenvalue profiles' and 'Learning Energy-Based Models by Self-normalising the Likelihood'. He also has an upcoming journal article titled 'Are ensembles getting better all the time?'. Additionally, he supervises several PhD students and postdocs.
Research Experience
- After his Ph.D., he did a postdoc at the IT University of Copenhagen, where he mainly worked with Jes Frellsen. Currently, he teaches at Université Côte d'Azur and is involved in organizing several workshops and summer schools.
Education
- He received his Ph.D. in applied mathematics from Université Paris Descartes (now called Université Paris Cité) in 2017. He worked at the MAP5 lab, where he was advised by Charles Bouveyron and Pierre Latouche.
Background
- His field of research is statistical machine learning, with a particular emphasis on hidden variables and model uncertainty. He is a research scientist at Inria and part of the Maasai (Models and Algorithms for Artificial Intelligence) team. He is also affiliated with the J.A. Dieudonné lab, which is the mathematics research department of Université Côte d'Azur. He holds a chair of the 3IA Côte d'Azur.
Miscellany
- He co-organizes and teaches at the Generative Modeling Summer School GeMSS.
