Professor Patrick Rebeschini

Professor of Statistics and Machine Learning

Biographical Sketch

I have a Ph.D. in Operations Research and Financial Engineering from Princeton University (2014). After that, I joined the Yale Institute for Network Science at Yale University. I worked two years as a Postdoctoral Associate in the Electrical Engineering Department, and one year as an Associate Research Scientist with a joint appointment as a Lecturer in the Computer Science Department at Yale.

Research Interests

My research interests lie at the intersection of probability, statistics, and computer science. I am interested in the investigation of fundamental principles in high-dimensional probability, statistics and optimisation to design computationally efficient and statistically optimal algorithms for machine learning.

Publications

Clerico, E., Flynn, H. and Rebeschini, P. (2025) “Uniform mean estimation for monotonic processes”, arXiv.

Vary, S., Martínez-Rubio, D. and Rebeschini, P. (2025) “Black-box uniform stability for non-Euclidean empirical risk minimization”, in. Artificial Intelligence and Statistics.

Buna-Marginean, A. and Rebeschini, P. (2025) “Robust gradient descent for phase retrieval”, in. PMLR.

Alfano, C. et al. (2025) “Learning mirror maps in policy mirror descent”, in.

Alfano, C. et al. (2025) “Learning mirror maps in policy mirror descent”, in. International Conference on Learning Representations.

Vary, S., Martínez-Rubio, D. and Rebeschini, P. (2024) “Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization”, arXiv.

Alfano, C. et al. (2024) “Learning Loss Landscapes in Preference Optimization”, arXiv.

Buna, A. and Rebeschini, P. (2024) “Robust Gradient Descent for Phase Retrieval”, arXiv.

Howard, S. et al. (2024) “Differentiable Cost-Parameterized Monge Map Estimators”, arXiv.

Huh, J. and Rebeschini, P. (2024) “Generalization bounds for label noise stochastic gradient descent”, in Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024). PMLR, pp. 1360–1368.

Contact Details

College affiliation: Tutorial Fellow at University College

Email: patrick.rebeschini@stats.ox.ac.uk

Web: https://www.stats.ox.ac.uk/~rebeschi/

Research Groups

Statistical Theory and Methodology

Computational Statistics and Machine Learning