Skip to yearly menu bar Skip to main content


(10 events)   Timezone:  
Show all
Toggle Poster Visibility
Oral
Thu Jun 13 03:00 AM -- 03:20 AM (KST) @ Room 104
Complexity of Linear Regions in Deep Networks
In Deep Learning Theory
Boris Hanin · David Rolnick
[ Video] 
Oral
Thu Jun 13 03:20 AM -- 03:25 AM (KST) @ Room 104
On Connected Sublevel Sets in Deep Learning
In Deep Learning Theory
Quynh Nguyen
[ Slides]  [ Video] 
Oral
Thu Jun 13 03:25 AM -- 03:30 AM (KST) @ Room 104
Adversarial Examples Are a Natural Consequence of Test Error in Noise
In Deep Learning Theory
Justin Gilmer · Nicolas Ford · Nicholas Carlini · Ekin Dogus Cubuk
[ Slides]  [ Video] 
Oral
Thu Jun 13 03:30 AM -- 03:35 AM (KST) @ Room 104
Greedy Layerwise Learning Can Scale To ImageNet
In Deep Learning Theory
Eugene Belilovsky · Michael Eickenberg · Edouard Oyallon
[ Slides]  [ Video] 
Oral
Thu Jun 13 03:35 AM -- 03:40 AM (KST) @ Room 104
On the Impact of the Activation function on Deep Neural Networks Training
In Deep Learning Theory
Soufiane Hayou · Arnaud Doucet · Judith Rousseau
[ Slides]  [ Video] 
Oral
Thu Jun 13 03:40 AM -- 04:00 AM (KST) @ Room 104
Estimating Information Flow in Deep Neural Networks
In Deep Learning Theory
Ziv Goldfeld · Ewout van den Berg · Kristjan Greenewald · Igor Melnyk · Nam Nguyen · Brian Kingsbury · Yury Polyanskiy
[ Slides]  [ Video] 
Oral
Thu Jun 13 04:00 AM -- 04:05 AM (KST) @ Room 104
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
In Deep Learning Theory
Zhanxing Zhu · Jingfeng Wu · Bing Yu · Lei Wu · Jinwen Ma
[ Slides]  [ Video] 
Oral
Thu Jun 13 04:05 AM -- 04:10 AM (KST) @ Room 104
Characterizing Well-Behaved vs. Pathological Deep Neural Networks
In Deep Learning Theory
Antoine Labatie
[ Slides]  [ Video] 
Oral
Thu Jun 13 04:10 AM -- 04:15 AM (KST) @ Room 104
Understanding Geometry of Encoder-Decoder CNNs
In Deep Learning Theory
Jong Chul Ye · woonkyoung Sung
[ Slides]  [ Video] 
Oral
Thu Jun 13 04:15 AM -- 04:20 AM (KST) @ Room 104
Traditional and Heavy Tailed Self Regularization in Neural Network Models
In Deep Learning Theory
Michael Mahoney · Charles H Martin
[ Slides]  [ Video]