77 citations · 204 across the 9 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.LG2017★ 36 cited
SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data
Alon Brutzkus, Amir Globerson, Eran Malach +1
Neural networks exhibit good generalization behavior in the over-parameterized regime, where the number of network parameters exceeds the number of observations. Nonetheless, curre…
cs.LG2017★ 77 cited
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
Alon Brutzkus, Amir Globerson
Deep learning models are often successfully trained using gradient descent, despite the worst case hardness of the underlying non-convex optimization problem. The key question is t…