Scalable kernel approximation
3 methods in the atlas attack this one problem. They are rivals: each wins something the others do not.
Phrasings that mean this problem
Scalable kernels
kernel-methods
- Nystrom approximationLandmark subsamplingstandardkernel-methods
- Random Fourier featuresShift-invariant samplingstandardkernel-methods
- Random binning featuresstandalonespecialistkernel-methods