Karim Lounici is a Professor of Statistics in the Department of Applied Mathematics at École polytechnique. His research focuses on the theoretical foundations of statistical models and algorithms, with a particular interest in complex and structured data.

His work spans high-dimensional statistics, spectral methods, operator learning, nonparametric statistics, bandits, unsupervised learning, and machine learning for science. More recently, his research has focused on operator learning for statistical inference and the forecasting of stochastic dynamical systems, with an emphasis on uncertainty quantification and interpretability.

Karim Lounici is also a Hi! PARIS Synergy Fellow for the 2025-2028 period, together with Florence D’Alché-Buc, Rémi Flamary, and Charlotte Laclau, on the project “Advancing Efficient, Reliable and Science-Informed Learning for Non-Euclidean Data with Application to Molecule and Biological Network Structures.” This fellowship focuses on non-Euclidean data, graphs, optimal transport, and representation learning.

His recent work includes research on Koopman operator regression for dynamical systems, learning infinitesimal generators of continuous-time Markov processes, and neural conditional probability operators for uncertainty quantification.