University of California Berkeley / store Computationally / University of Pennsylvania / Israel Institute of Technology / /
IndustryTerm
namely online convex optimization / modified algorithm / online gradient descent / ONLINE LEARNING Let / well-developed iterative algorithm / inner product / iterative algorithm / online learning / online linear optimization / Online Shortest Path / ellipsoid algorithm / iterative polynomial-time algorithms / bandit linear optimization algorithms / ONLINE LEARNING progress / deterministic algorithms / adversarial online learning / regret algorithm / matrix-vector product / online-learning problems / ONLINE LEARNING C. Computational Efficiency Algorithm / online convex optimization / online routing / online linear optimization problem / online optimization task / approximate solution / bandit algorithm / low-regret learning algorithms / travel time / simplest online learning strategy / Online Learning Jacob D. Abernethy / ONLINE LEARNING C. Vanilla Approach / Online Linear Optimization With Full Information The / generic template algorithm / regret minimization algorithm / learning algorithm / learning algorithms / computed solution / /
Organization
University of California / Defense Advanced Research Projects Agency / National Science Foundation / Department of Statistics / Department of Computer Science / University of Pennsylvania / Philadelphia / Department of Industrial Engineering and Operations Research / Israel Institute of Technology / Technion / /
Person
Jacob D. Abernethy / Elad Hazan / /
Position
Regularized Leader / player / Be The Regularized Leader / Associated Bounds Follow The Leader / Singer / Associate Editor / /
4164 IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 58, NO. 7, JULY 2012 Interior-Point Methods for Full-Information and Bandit Online Learning