Biological systems need to react stimuli over a broad spectrum of timescales. If and how this ability can emerge without external fine-tuning is puzzle. We consider here problem in discrete Markovian systems, where we leverage results from random matrix theory. Indeed, generic large transition matrices are governed by universal results, which predict the absence long timescales unless fine-tune...

We investigate the local spectral statistics of loss surface Hessians artificial neural networks, where we discover excellent agreement with Gaussian Orthogonal Ensemble across several network architectures and datasets. These results shed new light on applicability Random Matrix Theory to modelling networks suggest a previously unrecognised role for it in study surfaces deep learning. Inspired...