Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 8582-8591, 2019.
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
PPT (Upload PPT)