Skip to yearly menu bar Skip to main content


(6 events)   Timezone:  
Show all
Toggle Poster Visibility
Oral
Tue Dec 10 10:05 AM -- 10:20 AM (PST) @ West Exhibition Hall C + B3
Uniform convergence may be unable to explain generalization in deep learning
In Track 1 Session 1
Vaishnavh Nagarajan · J. Zico Kolter
Spotlight
Tue Dec 10 10:20 AM -- 10:25 AM (PST) @ West Exhibition Hall C + B3
On Exact Computation with an Infinitely Wide Neural Net
In Track 1 Session 1
Sanjeev Arora · Simon Du · Wei Hu · Zhiyuan Li · Russ Salakhutdinov · Ruosong Wang
[ Paper]  [ Poster]  [ Slides] 
Spotlight
Tue Dec 10 10:25 AM -- 10:30 AM (PST) @ West Exhibition Hall C + B3
Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
In Track 1 Session 1
Yuan Cao · Quanquan Gu
[ Paper]  [ Slides]  [ Slides] 
Spotlight
Tue Dec 10 10:30 AM -- 10:35 AM (PST) @ West Exhibition Hall C + B3
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks
In Track 1 Session 1
Mahyar Fazlyab · Alexander Robey · Hamed Hassani · Manfred Morari · George J. Pappas
[ Paper]  [ Slides]  [ Slides] 
Spotlight
Tue Dec 10 10:35 AM -- 10:40 AM (PST) @ West Exhibition Hall C + B3
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks
In Track 1 Session 1
Yuanzhi Li · Colin Wei · Tengyu Ma
[ Paper]  [ Slides]  [ Slides] 
Spotlight
Tue Dec 10 10:40 AM -- 10:45 AM (PST) @ West Exhibition Hall C + B3
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation
In Track 1 Session 1
Colin Wei · Tengyu Ma
[ Paper]  [ Slides]  [ Slides]