Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals

Sushrut Karmalkar
Sushrut Karmalkar

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 8582-8591, 2019.

Cited by: 8|Views13
EI

Abstract:

We consider the problem of computing the best-fitting ReLU with respect to square-loss on a training set when the examples have been drawn according to a spherical Gaussian distribution (the labels can be arbitrary). Let opt < 1 be the population loss of the best-fitting ReLU. We prove: Finding a ReLU with square-loss opt+. is as hard as ...More

Code:

Data:

Your rating :
0

 

Tags
Comments