The Optimal PAC Algorithm

@inproceedings{Warmuth2004TheOP,
  title={The Optimal PAC Algorithm},
  author={Manfred K. Warmuth},
  booktitle={COLT},
  year={2004}
}
Assume we are trying to learn a concept class C of VC dimension d with respect to an arbitrary distribution. There is PAC sample size bound that holds for any algorithm that always predicts with some consistent concept in the class C (BEHW89): O( ! (d log 1 ! +log 1 ! )), where ! and δ are the accuracy and confidence parameters. Thus after drawing this many examples (consistent with any concept in C), then with probability at least 1 − δ, the error of the produced concept is at most !. Here the… CONTINUE READING