The Extended Littlestone's Dimension for Learning with Mistakes and Abstentions
COLT, pp. 1584-1616, 2016.
This paper studies classification with an abstention option in the online setting. In this setting, examples arrive sequentially, the learner is given a hypothesis class H, and the goal of the learner is to either predict a label on each example or abstain, while ensuring that it does not make more than a pre-specified number of mistakes ...More
PPT (Upload PPT)