BIAU Gérard
Expertise
Discover the specialized technical skills and disciplinary affiliations of our members, who represent the federated communities of the Arts & Humanities, Science & Engineering, and Medicine within the Sorbonne University Alliance.
Activities
Overview the professional milestones, academic responsibilities, and international collaborations that drive our center’s double ambition to excel in both research and education.
Responsibilities
Gérard Biau is currently Director of SCAI (Sorbonne Center for Artificial Intelligence).
He is a Full Professor at the Probability, Statistics and Modelling Laboratory (LPSM) of Sorbonne University. His research is mainly focused in developing new methodologies and rigorous mathematical theories in statistical learning and AI, whilst trying to find connections between statistics and algorithms.
Awards
- Prix Marie-Jeanne Laurent Duhamel de la Société Française de Statistique (2003)
- Membre de l'Institut Universitaire de France (2012-2017)
Prix Michel-Montpetit-Inria de l'Académie des Sciences (2018)
Selected publications
1) Scornet, E., Biau, G. and Vert, J.-P. (2015). Consistency of random forests, The Annals of Statistics, Vol. 43, pp. 1716-1741
2) Biau, G., Bleakley, K. and Cadre, B. (2016). The statistical performance of collaborative inference, Journal of Machine Learning Research, Vol. 17 (62), pp. 1-29
3) Biau, G., Cadre, B. and Rouvière, L. (2019). Accelerated gradient boosting, Machine Learning, Vol. 108, pp. 971-992
4) Biau, G., Scornet, E. and Welbl, J. (2019). Neural random forests, Sankhya A, à paraître
5) Biau, G., Cadre, B., Sangnier, M. and Tanielian, U. (2019). Some theoretical properties of GANs, The Annals of Statistics, à paraître
International collaborations
McGill University (Canada)
Industrial collaborations
Criteo, Ecov, EDF, Safran, Safety Line.
Projects
Explore the specific interdisciplinary initiatives — ranging from industrial and European collaborations to innovative doctoral research — where our members apply their expertise to address the scientific challenges of tomorrow.