I am a research staff member of the Theory Group at the IBM Almaden Research Center.
I'm interested in using theoretical ideas to design efficient algorithms that are practical. Most of my research can be classified under "machine learning", though I'm also interested in computational learning theory, combinatorial and convex optimization, game theory and computational complexity.

Selected Publications

• On Stochastic and Worst-case Models for Investing. (with Satyen Kale) To appear in NIPS 2009.
  
• An Efficient Algorithm for Bandit Linear Optimization. (with Jacob Abernethy and Alexander Rakhlin) The 21st Annual Conference on Learning Theory (COLT 2008).
  IBM 2008 Pat Goldberg Memorial Best Paper Award
  COLT 2008 Machine Learning Journal Best Student Paper Award
  
• Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs. (with Satyen Kale) The 21st Annual Conference on Learning Theory (COLT 2008). Invited to special issue of Machine Learning Journal.
• Logarithmic Regret Algorithms for Online Convex Optimization. (with Amit Agarwal and Satyen Kale) In Machine Learning Journal Volume 69 , Issue 2-3 Pages: 169 - 192 (December 2007).
• HAPLOFREQ - Estimating Haplotype Frequencies Efficiently(with Eran Halperin) Special issue of Journal of Computational Biology,March 2006, Vol. 13, No. 2: 481-500. Extended abstract appeared in RECOMB 2005.
• (√(log n)) approximation to SPARSEST CUT can be found in Õ(n²) time. (with Sanjeev Arora and Satyen Kale.) In Proc. 45th FOCS, 238-247, 2004. Submitted to Siam Journal on Computing.


New ! draft of a short survey: The convex optimization approach to regret minimization.