Aymeric Dieuleveut is a Professor in Statistics and Machine Learning at École Polytechnique (CMAP, Institut Polytechnique de Paris) and Scientific Co-Director of Hi! PARIS. He is also a Hi! PARIS Fellow for the 2021-2024 period.

His work is centered on the mathematical foundations of machine learning, with a focus on stochastic algorithms, federated and decentralized learning, uncertainty quantification, missing data, and statistical learning theory. A recurring theme in his research is understanding how statistical and computational constraints interact at scale, and developing new tools and guarantees for methods used in practice.

His Hi! PARIS Fellowship project, Federated Learning: new Algorithms with Guarantees – FLAG, focused on the development of new algorithms for federated learning. This field aims to train machine learning models collaboratively across several organizations or devices while keeping data stored locally, responding to key challenges related to privacy, legal constraints, communication efficiency and distributed data. Learn more here.

After graduating from ENS Paris, he received his PhD from ENS Paris, in the Sierra team, supervised by Francis Bach, including a visiting period at UC Berkeley with Martin Wainwright. He then held a postdoctoral position at EPFL with Martin Jaggi. He joined École Polytechnique in 2019 as an Assistant Professor, defended his habilitation in 2023, and was promoted to Professor the same year.