Statistical Learning Theory
Investigators: Alexander (Sasha) Rakhlin
We study rates of convergence of learning algorithms. We investigate various complexity notions which lead to consistency of learning algorithms.
Recent papers on the subject:
J. Abernethy, A. Agarwal, P. Bartlett, and A. Rakhlin. A Stochastic View of Optimal Regret through Minimax Duality, COLT 2009.
A. Rakhlin, S. Mukherjee and T. Poggio. Stability Results in Learning Theory, Analysis and Applications, Special Issue on Learning Theory. Vol. 3, No. 4, 397-419. October 2005.
A. Caponnetto and A. Rakhlin. Stability Properties of Empirical Risk Minimization over Donsker Classes, Journal of Machine Learning Research. Vol. 7 (Dec), 2565--2583, 2006.
A. Rakhlin, D. Panchenko and S. Mukherjee. Risk Bounds for Mixture Density Estimation, ESAIM Probability and Statistics. Vol. 9, 220-229, June 2005.