Alexander Rakhlin
Assistant Professor of Statistics and
Computer and Information Science (CIS)
Honors and Awards: NSF CAREER Award - 2010
Research Expertise: Machine Learning
Alexander's research interests include developing efficient and optimal algorithms for online learning with limited feedback. He focuses on providing minimax guarantees for sequential optimization and studying the interplay of statistical accuracy and optimization complexity. He also focuses on developing methods for efficient regularization through random perturbation.
Member of:
Education:
PhD Biological and Computational Learning 2006 - Massachusetts Institute of Technology
Recent Publications 
- Stochastic convex optimization with bandit feedback, Agarwal, A. | Foster, D.P. | Hsu, D. | Kakade, S.M. | Rakhlin, A., SIAM Journal on Optimization, 2013
- Relax and randomize: From value to algorithms, Rakhlin, A. | Shamir, O. | Sridharan, K., Advances in Neural Information Processing Systems, 2012
- Making gradient descent optimal for strongly convex stochastic optimization, Rakhlin, A. | Shamir, O. | Sridharan, K., Proceedings of the 29th International Conference on Machine Learning, ICML 2012, 2012
- Foreword, Rakhlin, A., Journal of Computer and System Sciences, 2012
- Quantitative analysis of systems using game-theoretic learning, Seshia, S.A. | Rakhlin, A., Transactions on Embedded Computing Systems, 2012