0.25
0.5
0.75
1.25
1.5
1.75
2
Efficient Learning of Linear Separators under Bounded Noise
Published on Aug 20, 20151911 Views
We study the learnability of linear separators in $\Re^d$ in the presence of bounded (a.k.a Massart) noise. This is a realistic generalization of the random classification noise model, where the adver
Related categories
Chapter list
Efficient Learning of Halfspaces in the Presence of Bounded Noise00:00
Main result00:06
Computational Learning Theory and Statistical Learning Theory00:39
... it's not that easy!02:11
Hinge loss minimization does not work02:23
Our algorith02:47
See you at the poster!03:21