I'm interested in designing efficient algorithms for fundamental problems in machine learning and optimization. Most of my research can be classified under "machine learning", though I'm also interested in convex optimization, game theory and computational complexity.

Is optimization computationally equivalent to online learning?

SPOILER ALERT: this may be a decent answer :-)

Check out new grad-course book draft.

Together with Peter Grunwald, we're chairing the program for COLT 2015 , to be held Paris July 3-6.
Submit your groundbreaking work on learning theory!