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

Richards, D., Dobriban, E. and Rebeschini, P. (2021) “Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models?”, arXiv.

Wu, F. and Rebeschini, P. (2021) “Implicit Regularization in Matrix Sensing via Mirror Descent”, arXiv.

Wu, F. and Rebeschini, P. (2021) “Nearly Minimax-Optimal Rates for Noisy Sparse Phase Retrieval via Early-Stopped Mirror Descent”, arXiv.

Wu, F. and Rebeschini, P. (2020) “A continuous-time mirror descent approach to sparse phase retrieval”, in Advances in Neural Information Processing Systems 33 (NeurIPS 2020). Neural Information Processing Systems Foundation, Inc, pp. 1–12.

Vaškevičius, T., Kanade, V. and Rebeschini, P. (2020) “The statistical complexity of early-stopped mirror descent”, in. Neural Information Processing Systems Foundation, Inc, pp. 1–12.

Richards, D., Rebeschini, P. and Rosasco, L. (2020) “Decentralised learning with distributed gradient descent and random features”, in Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, pp. 8105–8115.

Wu, F. and Rebeschini, P. (2020) “A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval”, arXiv.

Richards, D., Rebeschini, P. and Rosasco, L. (2020) “Decentralised Learning with Random Features and Distributed Gradient Descent”, arXiv.

Wu, F. and Rebeschini, P. (2020) “Hadamard Wirtinger Flow for Sparse Phase Retrieval”, arXiv.

Vaškevičius, T., Kanade, V. and Rebeschini, P. (2020) “The Statistical Complexity of Early-Stopped Mirror Descent”, arXiv.

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