Computation and Statistics
Investigators: Alexander (Sasha) Rakhlin
In this project we study statistical guarantees for learning from examples together with the computational demands of the algorithms. This research is at the intersection of Optimization, Statistics, and Information Theory.
Recent papers on the subject:
M. Raginsky and A. Rakhlin. Information Complexity of Black-Box Convex Optimization: A New Look via Feedback Information Theory. Allerton Conference on Communication, Control, and Computing, 2009