Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability

NIPS 2020, 2020.

Cited by: 0|Views21
EI
Weibo:
Our results are perhaps most closely related to the notion of equal opportunity, where our experiments show that many off-the-shelf algorithms achieve high false negative rate on certain demographic groups when noise is added to the rest of the data

Abstract:

In this paper we revisit some classic problems on classification under misspecification. In particular, we study the problem of learning halfspaces under Massart noise with rate $\eta$. In a recent work, Diakonikolas, Goulekakis, and Tzamos resolved a long-standing problem by giving the first efficient algorithm for learning to accuracy $...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments