Robustly Learning a Single Neuron via Sharpness

06/13/2023
by   Puqian Wang, et al.
0

We study the problem of learning a single neuron with respect to the L_2^2-loss in the presence of adversarial label noise. We give an efficient algorithm that, for a broad family of activations including ReLUs, approximates the optimal L_2^2-error within a constant factor. Our algorithm applies under much milder distributional assumptions compared to prior work. The key ingredient enabling our results is a novel connection to local error bounds from optimization theory.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset