PPL
Yishay Mansour
Papers (5)
The Sample Complexity of Multiclass and Sparse Contextual BanditsTheoretical Foundations and Effective Algorithms for Policy-Aware Simulator LearningScale-Sensitive Shattering: Learnability and Evaluability at Optimal ScaleCollaborating in Multi-Armed Bandits with Strategic AgentsOnline Set Learning from Precision and Recall Feedback