Alexander Rakhlin

Education

PhD, MIT 2006
BA, Cornell University, 2000

Academic Positions Held

Wharton : 2009present
Previous Appointments:   University of California, Berkeley

For more information, go to My Personal Page

Alexander Rakhlin, BISTRO: An Efficient RelaxationBased Method for Contextual Bandits_.

Tony Cai, Tengyuan Liang, Alexander Rakhlin.

Tony Cai, Tengyuan Liang, Alexander Rakhlin, Geometric Inference for General HighDimensional Linear Inverse Problems, The Annals of Statistics, 44, pp. 15361563.

Alexander Rakhlin, Empirical Entropy, Minimax Regret and Minimax Risk.

Dean P. Foster, Alexander Rakhlin, Adaptive Online Learning.

Alexander Rakhlin, Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints, COLT 2015.

Alexandre Belloni, Tengyuan Liang, Hariharan Narayanan, Alexander Rakhlin, Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions 40, pp. 240265.

Tengyuan Liang, Alexander Rakhlin, Learning with Square Loss: Localization through Offset Rademacher Complexity 40, pp. 12601285.

Ali Jadbabaie, Alexander Rakhlin, Online Optimization: Competing with Dynamic Comparators, AISTATS.

Alexander Rakhlin data. In particular, the focus is on characterizing the generalization ability of learning algorithms in terms of how well they perform on "new" data when trained on some given data set. The focus of the course is on: providing the fundamental tools used in this analysis; understanding the performance of widely used learning algorithms; understanding the "art" of designing good algorithms, both in terms of statistical and computational properties. Potential topics include: empirical process theory; online learning; stochastic optimization; margin based algorithms; feature selection; concentration of measure.

STAT991 SEM IN ADV APPL OF STAT

This seminar will be taken by doctoral candidates after the completion of most of their coursework. Topics vary from year to year and are chosen from advance probability, statistical inference, robust methods, and decision theory with principal emphasis on applications.

• Best Paper Award, Conference on Learning Theory, 2011
• NSF CAREER Award, Division of Mathematical Sciences, 2010
• IBM Research’s Pat Goldberg Memorial Best Paper Award in CE, EE and Math, 2008