Tutorial Fellow in Statistics; Associate Professor of Statistics
In Univ I teach all the first year and second year core courses in probability and statistics. In Hilary 2018 I will be teaching Advanced Simulations Methods for Part C and MSc students in the Department of Statistics.
My research interests lie at the intersection of applied probability, statistics, and computer science. I am interested in the investigation of fundamental principles to perform scalable inference, learning, and optimization in high-dimensional models, and in the design and analysis of algorithms in distributed machine learning, with applications to graphical models and Monte Carlo methods.
P. Rebeschini and S. Tatikonda, Accelerated Consensus via Min-Sum Splitting, to appear.
P. Rebeschini and S. Tatikonda, A new approach to Laplacian solvers and flow problems, to appear.
P. Rebeschini and A. Karbasi, Fast mixing for discrete point processes, 28th Annual Conference on Learning Theory (COLT) (2015).
P. Rebeschini and R. van Handel, Can local particle filters beat the curse of dimensionality?, Ann. Appl. Probab. 25, No. 5, 2809–2866 (2015).
P. Rebeschini and R. van Handel, Comparison theorems for Gibbs measures, J. Stat. Phys. 157, 234-281 (2014).