Efficient active learning of sparse halfspaces

conference on learning theory, 2018.

Cited by: 9|Views14
EI

Abstract:

We study the problem of efficient PAC active learning of d-dimensional linear classifiers, where the goal is to learn a classifier with low error, using as few label queries as possible. Given the extra assumption that there is a t-sparse linear separator that peforms well on the data (t

Code:

Data:

Your rating :
0

 

Tags
Comments