Skip to yearly menu bar Skip to main content


(4 events)   Time zone: Conference local time zone  
Show all
Toggle Poster Visibility
Oral
Fri Jul 13 11:00 AM -- 11:20 AM (CEST) @ K1
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
In Deep Learning (Theory) 6
Itay Safran · Ohad Shamir
[ PDF]  [ Video] 
Oral
Fri Jul 13 11:20 AM -- 11:40 AM (CEST) @ K1
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks
In Deep Learning (Theory) 6
Peter Bartlett · Dave Helmbold · Phil Long
[ PDF]  [ Video] 
Oral
Fri Jul 13 11:40 AM -- 11:50 AM (CEST) @ K1
On the Power of Over-parametrization in Neural Networks with Quadratic Activation
In Deep Learning (Theory) 6
Simon Du · Jason Lee
[ PDF]  [ Video] 
Oral
Fri Jul 13 11:50 AM -- 12:00 PM (CEST) @ K1
Optimization Landscape and Expressivity of Deep CNNs
In Deep Learning (Theory) 6
Quynh Nguyen · Matthias Hein
[ PDF]  [ Video]