Agnostic Proper Learning of Halfspaces under Gaussian Marginals

02/10/2021
by   Ilias Diakonikolas, et al.
5

We study the problem of agnostically learning halfspaces under the Gaussian distribution. Our main result is the first proper learning algorithm for this problem whose sample complexity and computational complexity qualitatively match those of the best known improper agnostic learner. Building on this result, we also obtain the first proper polynomial-time approximation scheme (PTAS) for agnostically learning homogeneous halfspaces. Our techniques naturally extend to agnostically learning linear models with respect to other non-linear activations, yielding in particular the first proper agnostic algorithm for ReLU regression.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset