4   Show all »
Toggle Poster Visibility
Oral
Fri Jul 13th 11:00 -- 11:20 AM @ K1
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
Itay Safran · Ohad Shamir
Oral
Fri Jul 13th 11:20 -- 11:40 AM @ K1
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks
Peter Bartlett · Dave Helmbold · Phil Long
Oral
Fri Jul 13th 11:40 -- 11:50 AM @ K1
On the Power of Over-parametrization in Neural Networks with Quadratic Activation
Simon Du · Jason Lee
Oral
Fri Jul 13th 11:50 AM -- 12:00 PM @ K1
Optimization Landscape and Expressivity of Deep CNNs
Quynh Nguyen · Matthias Hein