C. Seshadhri

Publications (3)0 Total impact

• Source

  Available from: psu.edu

  Conference Proceeding: Efficient learning algorithms for changing environments.

  Elad Hazan, C. Seshadhri
  Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, Montreal, Quebec, Canada, June 14-18, 2009; 01/2009
• Source

  Available from: psu.edu

  Article: Adaptive Algorithms for Online Decision Problems.

  Elad Hazan, C. Seshadhri
  Electronic Colloquium on Computational Complexity (ECCC). 01/2007; 14.
• Source

  Available from: psu.edu

  Article: Adaptive Algorithms for Online Optimization

  Elad Hazan, C Seshadhri
  [show abstract] [hide abstract]
  ABSTRACT: We study the notion of learning in an oblivious changing environment. Existing online learning algorithms which minimize regret are shown to converge to the average of all locally optimal solutions. We propose a new performance metric, strengthening the standard metric of regret, to capture convergence to locally optimal solutions. We then describe a series of reductions which transform algorithms for minimizing (standard) regret into adaptive algorithms albeit incurring only poly-logarithmic computational overhead. We describe applications of this technique to various well studied online problems, such as portfolio management, online routing and the tree update problem. In all cases we explain how previous algorithms perform suboptimally and how the reduction technique gives adaptive algorithms. Our reductions combine techniques from data streaming algorithms, composition of learning algorithms and a novel use of unbiased gradient estimates.
  01/2007; 88.