A Law of Robustness for Two-Layers Neural Networks

Dr. Sébastien Bubeck will present a mathematical conjecture potentially establishing overparametrization as a law of robustness for neural networks. He will tell you some of the things that we already know about this conjecture. Time-permitting he 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