A general lower bound on the number of examples needed for learning

Given a p-concept classC, we define two important functionsdC( ),d C( ) (related to the notion of -shattering). We prove a lower bound of ((dC( ) 1)/( 2)) on the number of examples required for learningCwith an ( , )-good model of probability. We prove ...

This paper presents a general information-theoretic approach for obtaining lower bounds on the number of examples required for Probably Approximately Correct (PAC) learning in the presence of noise. This approach deals directly with the fundamental ...

We consider the complexity of concept learning in various common models for on-line learning, focusing on methods for proving lower bounds to the learning complexity of a concept class. Among others, we consider the model for learning with equivalence ...