this work references cited by second hopReferences
- 1997A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting20,469 cited
- 2002Finite-time Analysis of the Multiarmed Bandit Problem5,980 cited
- 2006Prediction, Learning, and Games3,176 cited
- 2002The Nonstochastic Multiarmed Bandit Problem2,210 cited
- 1952Some aspects of the sequential design of experiments2,183 cited
- 2003Online convex programming and generalized infinitesimal gradient ascent1,733 cited
- 2012Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems1,410 cited
- 2013Ad click prediction870 cited
- 1997Exponentiated Gradient versus Gradient Descent for Linear Predictors856 cited
- 2007The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information426 cited
- 2004Minimax policies for adversarial and stochastic bandits330 cited
- 2001Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions297 cited
- 2007Online Learning: Theory, Algorithms, and Applications297 cited
- 1987Adaptive Treatment Allocation and the Multi-Armed Bandit Problem279 cited
- 2010Adaptive Bound Optimization for Online Convex Optimization228 cited
Only edges whose both ends are imported exist here. Widen the year window, or show the whole map. Back to the work