Trading off Mistakes and Don't-Know Predictions

Part of Advances in Neural Information Processing Systems 23 (NIPS 2010)

Bibtex »Metadata »Paper »

Authors

Amin Sayedi, Morteza Zadimoghaddam, Avrim Blum

Abstract

We discuss an online learning framework in which the agent is allowed to say I don't know'' as well as making incorrect predictions on given examples. We analyze the trade off between sayingI don't know'' and making mistakes. If the number of don't know predictions is forced to be zero, the model reduces to the well-known mistake-bound model introduced by Littlestone [Lit88]. On the other hand, if no mistakes are allowed, the model reduces to KWIK framework introduced by Li et. al. [LLW08]. We propose a general, though inefficient, algorithm for general finite concept classes that minimizes the number of don't-know predictions if a certain number of mistakes are allowed. We then present specific polynomial-time algorithms for the concept classes of monotone disjunctions and linear separators.