Toggle Poster Visibility
Oral
Fri Jul 13 02:00 AM -- 02:20 AM (PDT) @ K1
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
Oral
Fri Jul 13 02:20 AM -- 02:40 AM (PDT) @ K1
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks
Oral
Fri Jul 13 02:40 AM -- 02:50 AM (PDT) @ K1
On the Power of Over-parametrization in Neural Networks with Quadratic Activation
Oral
Fri Jul 13 02:50 AM -- 03:00 AM (PDT) @ K1
Optimization Landscape and Expressivity of Deep CNNs