Personal profile
Personal profile
He is a Professor in Statistics and Learning at École Polytechnique, Palaiseau, in the Applied Mathematics Department.
Before that, he was a postdoctoral researcher at EPFL (École Polytechnique Fédérale de Lausanne), in the MLO team, directed by Martin Jaggi. Prior to that, he was a Ph.D. student in the Sierra team, which is part of the DI/ENS (Computer Science Department of École Normale Supérieure), under the supervision of Francis Bach. He graduated from École Normale Supérieure de Paris (Ulm) in 2014 and obtained a Master’s degree in Mathematics, Probability and Statistics at Université Paris-Sud (Orsay).
From March to August 2016, he was a visiting scholar researcher at the University of California, Berkeley, under the supervision of Martin Wainwright.
Research interests
- Statistics
- Optimization
- Stochastic approximation
- Federated Learning
- Uncertainty Quantification
- High-dimensional learning
- Non-parametric statistics
- Scalable kernel methods
Fingerprint
- 1 Similar Profiles
Collaborations and top research areas from the last five years
-
Byzantine-Robust Gossip: Insights from a Dual Approach
Gaucher, R., Dieuleveut, A. & Hendrikx, H., 1 Jan 2026, In: Transactions on Machine Learning Research. 2026-FebruaryResearch output: Contribution to journal › Article › peer-review
-
Provable non-accelerations of the heavy-ball method
Goujaud, B., Taylor, A. & Dieuleveut, A., 1 Jan 2025, (Accepted/In press) In: Mathematical Programming.Research output: Contribution to journal › Article › peer-review
-
Refined Analysis of Constant Step Size Federated Averaging and Federated Richardson-Romberg Extrapolation
Mangold, P., Durmus, A., Dieuleveut, A., Samsonov, S. & Moulines, E., 1 Jan 2025, In: Proceedings of Machine Learning Research. 258, p. 5023-5031 9 p.Research output: Contribution to journal › Conference article › peer-review
-
Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
Mangold, P., Durmus, A., Dieuleveut, A. & Moulines, E., 1 Jan 2025, In: Proceedings of Machine Learning Research. 267, p. 42902-42946 45 p.Research output: Contribution to journal › Conference article › peer-review
-
Unified Breakdown Analysis for Byzantine Robust Gossip
Gaucher, R., Dieuleveut, A. & Hendrikx, H., 1 Jan 2025, In: Proceedings of Machine Learning Research. 267, p. 18868-18896 29 p.Research output: Contribution to journal › Conference article › peer-review
-
Compressed and distributed least-squares regression: convergence rates with applications to federated learning
Philippenko, C. & Dieuleveut, A., 1 Jan 2024, In: Journal of Machine Learning Research. 25Research output: Contribution to journal › Article › peer-review
-
Compression with Exact Error Distribution for Federated Learning
Hegazy, M., Leluc, R., Li, C. T. & Dieuleveut, A., 1 Jan 2024, In: Proceedings of Machine Learning Research. 238, p. 613-621 9 p.Research output: Contribution to journal › Conference article › peer-review
-
PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python
Goujaud, B., Moucer, C., Glineur, F., Hendrickx, J. M., Taylor, A. B. & Dieuleveut, A., 1 Sept 2024, In: Mathematical Programming Computation. 16, 3, p. 337-367 31 p.Research output: Contribution to journal › Article › peer-review
Open Access -
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
Ferbach, D., Goujaud, B., Gidel, G. & Dieuleveut, A., 1 Jan 2024, In: Proceedings of Machine Learning Research. 238, p. 3853-3861 9 p.Research output: Contribution to journal › Conference article › peer-review
-
Random features models: a way to study the success of naive imputation
Ayme, A., Boyer, C., Dieuleveut, A. & Scornet, E., 1 Jan 2024, In: Proceedings of Machine Learning Research. 235, p. 2108-2134 27 p.Research output: Contribution to journal › Conference article › peer-review