Publications

Preprints

• J. Mourtada. Universal coding, intrinsic volumes, and metric complexity. Preprint, 2023. [PDF] [arXiv]

Journal articles

• J. Mourtada, L. Rosasco. An elementary analysis of ridge regression with random design. Comptes Rendus Mathématique, 360:1055–1063, 2022. [PDF] [Link] [arXiv]

• J. Mourtada, T. Vaškevičius, N. Zhivotovskiy. Distribution-free robust linear regression. Mathematical Statistics and Learning, 4(3):253–292, 2021. [PDF] [Link] [arXiv] [Slides]

• J. Mourtada, S. Gaïffas. An improper estimator with optimal excess risk in misspecified density estimation and logistic regression. Journal of Machine Learning Research, 23(31):1–49, 2022. [PDF] [Link] [arXiv] [Slides]

• J. Mourtada. Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices. Annals of Statistics, 50(4):2157–2178, 2022. [PDF] [Link] [arXiv]

• J. Mourtada, S. Gaïffas, E. Scornet. AMF: Aggregated Mondrian forests for online learning. Journal of the Royal Statistical Society: Series B, 83(3):505–533, 2021. [PDF] [Link] [arXiv]

• J. Mourtada, S. Gaïffas. On the optimality of the Hedge algorithm in the stochastic regime. Journal of Machine Learning Research, 20(83):1−28, 2019. [PDF] [Link] [arXiv] [Slides]

• J. Mourtada, S. Gaïffas, E. Scornet. Minimax optimal rates for Mondrian trees and forests. Annals of Statistics, 48(4):2253−2276, 2020. [PDF] [Link] [arXiv]

Conference proceedings

Preliminary conference versions of journal papers are indicated as “extended abstracts”; see the list above for final versions.

• J. Mourtada, T. Vaškevičius, N. Zhivotovskiy. Local risk bounds for statistical aggregation. Extended abstract in Proceedings of the 36th Conference on Learning Theory, PMLR 195:5697-5698, 2023. [Link] [arXiv]

• D. Richards, J. Mourtada, L. Rosasco. Asymptotics of ridge(less) regression under general source condition. Proceedings of the 24th international conference on Artificial Intelligence and Statistics, PMLR 130:3889-3897, 2021. [Link] [arXiv]

• A. Della Vecchia, J. Mourtada, E. De Vito, L. Rosasco. Regularized ERM on random subspaces. Proceedings of the 24th international conference on Artificial Intelligence and Statistics, PMLR 130:4006-4014, 2021. [Link] [arXiv]

• (Extended abstract) J. Mourtada, S. Gaïffas, E. Scornet. Universal consistency and minimax rates for online Mondrian Forests. In Advances in Neural Information Processing Systems, 2017. [PDF] [Link] [arXiv]

• J. Mourtada, O.-A. Maillard. Efficient tracking of a growing number of experts. In Proceedings of the 28th international conference on Algorithmic Learning Theory, PMLR 76:517-539, 2017. [PDF] [Link] [arXiv] [Slides]

Dissertations

• My PhD dissertation Contributions to statistical learning: density estimation, expert aggregation and random forests (the introduction is in French, the rest in English), prepared at École polytechnique, supervised by Stéphane Gaïffas and Erwan Scornet, and defended on June 8th, 2020. Here are the slides of the defense, and here is a short survey article (in French) for MATAPLI.

• My Masters dissertation in Mathematics (Probability): Prédiction séquentielle par agrégation d'experts (Sequential prediction through expert aggregation, in French), supervised by Odalric-ambrym Maillard. Summer 2016.

• My Masters dissertation in Mathematics: Morphismes entre groupes de difféomorphismes de variétés (Morphisms between diffeomorphism groups of manifolds, in French), supervised by Frédéric Le Roux. Summer 2015. Here is a short introduction to the subject: Structure algébrique des groupes de difféomorphismes.

• My first year dissertation at ENS, with Thomas Budzinski: Diamètre des groupes de permutations, supervised by Harald Andrés Helfgott. Spring 2013.