Efficient active learning of sparse halfspaces with arbitrary bounded noise

NIPS 2020, 2020.

Cited by: 2|Views25
EI
Weibo:
We develop an attribute-efficient learning algorithm that runs in polynomial time, and achieves a label complexity of Os 4

Abstract:

In this work we study active learning of homogeneous $s$-sparse halfspaces in $\mathbb{R}^d$ under label noise. Even in the absence of label noise this is a challenging problem and only recently have label complexity bounds of the form $\tilde{O} \left(s \cdot \mathrm{polylog}(d, \frac{1}{\epsilon}) \right)$ been established in \citet{z...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments