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

Alfano, C. and Rebeschini, P. (2022) “Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization”, arXiv.

Oravkin, E. and Rebeschini, P. (2022) “On optimal interpolation in linear regression”, in. Neural Information Processing Systems Foundation, pp. 29116–29128.

Kanade, V., Rebeschini, P. and Vaskevicius, T. (2022) “Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition”, arXiv.

Wu, F. and Rebeschini, P. (2021) “Implicit regularization in matrix sensing via mirror descent”, in Advances in Neural Information Processing Systems 34 (NeurIPS 2021). Neural Information Processing Systems Foundation.

Farghly, T. and Rebeschini, P. (2021) “Time-independent generalization bounds for SGLD in non-convex settings”, in Advances in Neural Information Processing Systems 34 (NeurIPS 2021). Neural Information Processing Systems Foundation, pp. 19836–19846.

Richards, D., Negahban, S. and Rebeschini, P. (2021) “Distributed machine learning with sparse heterogeneous data”, in Advances in Neural Information Processing Systems 34 (NeurIPS 2021). Neural Information Processing Systems Foundation, pp. 18008–18020.

Farghly, T. and Rebeschini, P. (2021) “Time-independent Generalization Bounds for SGLD in Non-convex Settings”, arXiv.

Oravkin, E. and Rebeschini, P. (2021) “On Optimal Interpolation In Linear Regression”, arXiv.

Alfano, C. and Rebeschini, P. (2021) “Dimension-Free Rates for Natural Policy Gradient in Multi-Agent Reinforcement Learning”, arXiv.

Wu, F. and Rebeschini, P. (2021) “Hadamard wirtinger flow for sparse phase retrieval”, in Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021). Journal of Machine Learning Research, pp. 982–990.

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