Sign in
[NeurIPS 2021Outstanding Paper] A Universal Law of Robustness
Aug 24, 2021
|
68 views
Sebastien Bubeck
Follow
Details
I give a tentative theoretical justification for why large overparametrization is important in neural networks. Primarily based on "A Universal Law of Robustness via Isoperimetry" by S.B. and Mark Sellke.
https://arxiv.org/abs/2105.12806
Category: New This Week
Category: NeurIPS 2021
Comments
loading...
Reactions
(0)
| Note
📝 No reactions yet
Be the first one to share your thoughts!
Reactions
(0)
Note
loading...
Recommended
18:33
ICAPS 2014: Stefan Edelkamp on "Symbolic and Explicit Search Hybrid through Perfect Hash Functions"
ICAPS
| Aug 7, 2014
50:27
ICAPS 2012: Invited Talk by Anthony Cohn
ICAPS
| Aug 15, 2014
56:04
ICAPS 2012: Invited talk by George Pappas
ICAPS
| Aug 18, 2014
51:45
ICAPS 2012: Opening Remark & Invited Talk by Robert Ambrose
ICAPS
| Aug 18, 2014
23:37
ICAPS 2012: Session Ia on "Temporal Planning & Scheduling"
ICAPS
| Aug 18, 2014