Exponential Savings in Agnostic Active Learning through Abstention
Abstract
We show that in poolbased active classification without assumptions on the underlying distribution, if the learner is given the power to abstain from some predictions by paying the price marginally smaller than the average loss $1/2$ of a random guess, exponential savings in the number of label requests are possible whenever they are possible in the corresponding realizable problem. We extend this result to provide a necessary and sufficient condition for exponential savings in poolbased active classification under the model misspecification.
 Publication:

arXiv eprints
 Pub Date:
 January 2021
 arXiv:
 arXiv:2102.00451
 Bibcode:
 2021arXiv210200451P
 Keywords:

 Computer Science  Machine Learning;
 Computer Science  Information Theory;
 Mathematics  Statistics Theory
 EPrint:
 31 pages, IEEE Transactions on Information Theory