arXiv stat.ML
· Papers
A law of robustness for two-layer neural networks with arbitrary weights
arXiv:2607.07778v1 Announce Type: cross Abstract: Bubeck, Li and Nagaraj conjectured that, for generic data, any two-layer neural network with $m$ neurons that fits $n$ noisy labels must have Lipschitz constant at least of order $sqrt{n/m}$, with no restriction on the size of the weights. Bubeck and Sellke proved a un