PPL
Steve Hanneke
Papers (5)
PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable SettingWhat is Learnable in Valiant's Theory of the Learnable?On Characterizing Learnability for Adversarial Noisy BanditsRegret-Oracle Complexity Tradeoffs in Agnostic Online LearningRealizable Bayes-Consistency for General Metric Losses