CS 2750 Machine
Learning

PAC Learnability

•There
exists a learning algorithm that **efficiently** learns the classification
with a pre-specified **accuracy and confidence
**

•A
learning algorithm *P *that given an arbitrary

–classification
error e
(<1/2), and

–confidence
d (<1/2)

•Outputs
a classifier

–With
a classification accuracy > (1-e)

–A
confidence probability > (1- d)

–And
runs in time polynomial in 1/ d, 1/e

•Implies:
number of samples *N* is polynomial in 1/ d, 1/e