[NeurIPS 2021Outstanding Paper] A Universal Law of Robustness

Aug 24, 2021

|

67 views

Sebastien Bubeck

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

ICAPS 2014: Ron Alford on "On the Feasibility of Planning Graph Style Heuristics for HTN Planning"

ICAPS | Aug 6, 2014

ICAPS 2014: Mike Barley on "Overcoming the Utility Problem in Heuristic Generation: ..."

ICAPS | Aug 7, 2014

ICAPS 2014: Stefan Edelkamp on "Symbolic and Explicit Search Hybrid through Perfect Hash Functions"

ICAPS | Aug 7, 2014

ICAPS 2012: Invited Talk by Anthony Cohn

ICAPS | Aug 15, 2014

ICAPS 2012: Invited talk by George Pappas

ICAPS | Aug 18, 2014