[NeurIPS 2021Outstanding Paper] A Universal Law of Robustness

Aug 24, 2021

|

66 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

SREcon15 - Architecting and Launching the Halo 4 Services

USENIX | Apr 13, 2015

SREcon15 - Being Afraid—How Paranoia at Dropbox Protects Your Data

USENIX | Apr 13, 2015

ICAPS 2014: Jendrik Seipp on "Diverse and Additive Cartesian Abstraction Heuristics"

ICAPS | Apr 14, 2015

ICAPS 2014: Bram Ridder on "Heuristic Evaluation Based on Lifted Relaxed Planning Graphs"

ICAPS | Apr 14, 2015

ICAPS 2014: Richard Valenzano on "A Comparison of Knowledge-Based GBFS Enhancements and..."

ICAPS | Apr 15, 2015