Sciweavers

16 search results - page 1 / 4
» Learning Halfspaces with Malicious Noise
Sort
View
ICALP
2009
Springer
14 years 5 months ago
Learning Halfspaces with Malicious Noise
We give new algorithms for learning halfspaces in the challenging malicious noise model, where an adversary may corrupt both the labels and the underlying distribution of examples....
Adam R. Klivans, Philip M. Long, Rocco A. Servedio
FOCS
2006
IEEE
13 years 11 months ago
Hardness of Learning Halfspaces with Noise
Learning an unknown halfspace (also called a perceptron) from labeled examples is one of the classic problems in machine learning. In the noise-free case, when a halfspace consist...
Venkatesan Guruswami, Prasad Raghavendra
FOCS
2006
IEEE
13 years 11 months ago
New Results for Learning Noisy Parities and Halfspaces
We address well-studied problems concerning the learnability of parities and halfspaces in the presence of classification noise. Learning of parities under the uniform distributi...
Vitaly Feldman, Parikshit Gopalan, Subhash Khot, A...
IPL
2011
131views more  IPL 2011»
12 years 11 months ago
The regularized least squares algorithm and the problem of learning halfspaces
We provide sample complexity of the problem of learning halfspaces with monotonic noise, using the regularized least squares algorithm in the reproducing kernel Hilbert spaces (RKH...
Ha Quang Minh