Statistics and Optimization

Head of the team : Pierre Neuvial. Permanent members.

The scientific activity of the team is based on various themes in applied mathematics. We can distinguish the following main themes (naturally overlapping):

  • mathematical statistics: processes, distances and Wasserstein spaces, parametric, semi-parametric and non-parametric estimation, high-dimensional statistics, survival, extremes, mixture models, test theory and multiple tests, separation rates, functional data analysis;

  • statistical learning: sequential learning, massive data learning, Bayesian learning, deep learning, fairness (algorithm bias, data confidentiality), computational aspects (stochastic optimization, Monte Carlo sampling), computer experiments;

  • optimization: shape optimization, optimal transport, surface representation, image processing, inverse problems, optimal control, numerical optimization;

  • statistics for industry, biology and health (genomics, biostatistics, epidemiology): sensitivity analysis, detection of atypical regions, detection of breaks, supervised and unsupervised classification, remote sensing. Contributions cover modeling, inference, as well as methodological, algorithmic and software developments.

Interactions :

Many members of the team interact with other IMT teams, and more broadly with the Toulouse research ecosystem, either through ad hoc or more structured collaborations, notably via

Team Life :

The Statistics and Optimization seminar takes place every Tuesday at 11:15 am.