Umar Syed

I received a Ph.D. in Computer Science from Princeton University, where I was advised by Rob Schapire. I spent two years as a postdoctoral researcher at the University of Pennsylvania, hosted by Ben Taskar and Michael Kearns. My research interests are in machine learning.

Google Publications

Previous Publications

  •  

    An $\tildeO(\frac1\sqrtT)$-error online algorithm for retrieving heavily perturbated statistical databases in the low-dimensional querying mode

    Krzysztof Choromanski, Afshin Rostamizadeh, Umar Syed

    CoRR, vol. abs/1504.01117 (2015)

  •  

    Bandits, query learning, and the haystack dimension

    Kareem Amin, Michael Kearns, Umar Syed

    Proceedings of the Twenty-Fourth Annual Conference on Learning Theory (COLT 2011)

  •  

    Graphical models for bandit problems

    Kareem Amin, Michael Kearns, Umar Syed

    Uncertainty in Artificial Intelligence: Proceedings of the Twenty-Seventh Conference (UAI 2011)

  •  

    There's something about MRAI: Timing diversity can exponentially worsen BGP convergence

    Alex Fabrikant, Umar Syed, Jennifer Rexford

    Proceedings of the Thirtieth IEEE International Conference on Computer Communications (INFOCOM 2011)

  •  

    A reduction from apprenticeship learning to classification

    Umar Syed, Robert E. Schapire

    Advances in Neural Information Processing Systems 24 (NIPS 2010)

  •  

    Private and third-party randomization in risk-sensitive equilibrium concepts

    Mickey Brautbar, Michael Kearns, Umar Syed

    Proceedings of the Twenty-Fourth Conference on Artificial Intelligence (AAAI 2010)

  •  

    Semi-supervised learning with adversarially missing label information

    Umar Syed, Ben Taskar

    Advances in Neural Information Processing Systems 24 (NIPS 2010)

  •  

    Adapting to the shifting intent of search queries

    Umar Syed, Aleksandrs Slivkins, Nina Mishra

    Advances in Neural Information Processing Systems 23 (NIPS 2009)

  •  

    Apprenticeship learning using linear programming

    Umar Syed, Michael Bowling, Robert E. Schapire

    Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML 2008)

  •  

    Enzyme function prediction with interpretable models

    Umar Syed, Golan Yona

    Methods in Molecular Biology: Computational Systems Biology, Humana Press (2008)

  •  

    Using automatically transcribed dialogs to learn user models in a spoken dialog system

    Umar Syed, Jason Williams

    Proceedings of the Forty-Sixth Annual Meeting of the Association for Computational Linguistics (ACL 2008)

  •  

    A game-theoretic approach to apprenticeship learning

    Umar Syed, Robert E. Schapire

    Advances in Neural Information Processing Systems 21 (NIPS 2007)

  •  

    Imitation learning with a value-based prior

    Umar Syed, Robert E. Schapire

    Uncertainty in Artificial Intelligence: Proceedings of the Twenty-Third Conference (UAI 2007)

  •  

    Using a mixture of probabilistic decisions trees for direct prediction of protein function

    Umar Syed, Golan Yona

    Proceedings of the Seventh Annual International Conference on Research in Computational Biology (RECOMB 2003)