Systems | Information | Learning | Optimization
 

A law of robustness for two-layers neural networks

Abstract:
I will present a mathematical conjecture potentially establishing overparametrization as a law of robustness for neural networks. I will tell you some of the things that we already know about this conjecture. Time-permitting I will include a discussion of how to think about various quantities for higher order tensors (their rank, the relation between spectral norm and nuclear norm, and concentration for random tensors).

Joint work with Yuanzhi Li and Dheeraj Nagaraj
https://arxiv.org/abs/2009.14444

March 17 @ 12:30
12:30 pm (1h)

Remote

Sebastien Bubeck