Learning geometric concepts with nasty noise

STOC '18: Symposium on Theory of Computing Los Angeles CA USA June, 2018, pp. 1061-1073, 2018.

Cited by: 33|Bibtex|Views5|Links
EI

Abstract:

We study the efficient learnability of geometric concept classes — specifically, low-degree polynomial threshold functions (PTFs) and intersections of halfspaces — when a fraction of the training data is adversarially corrupted. We give the first polynomial-time PAC learning algorithms for these concept classes with dimension-independent...More

Code:

Data:

Your rating :
0

 

Tags
Comments