no code implementations • 3 Jun 2023 • Nicholas P Baskerville
Informed by the historical applications of random matrix theory in physics and elsewhere, we establish the presence of local random matrix universality in real neural networks and then utilise this as a modeling assumption to derive powerful and novel results about the Hessians of neural network loss surfaces and their spectra.
no code implementations • 17 May 2022 • Nicholas P Baskerville, Jonathan P Keating, Francesco Mezzadri, Joseph Najnudel, Diego Granziol
This paper considers several aspects of random matrix universality in deep neural networks.
no code implementations • 15 Mar 2022 • Nicholas P Baskerville
Determinantal points processes are a promising but relatively under-developed tool in machine learning and statistical modelling, being the canonical statistical example of distributions with repulsion.
1 code implementation • 12 Feb 2021 • Nicholas P Baskerville, Diego Granziol, Jonathan P Keating
We further investigate the importance of the true loss surface in neural networks and find, in contrast to previous work, that the exponential hardness of locating the global minimum has practical consequences for achieving state of the art performance.
1 code implementation • 7 Jan 2021 • Nicholas P Baskerville, Jonathan P Keating, Francesco Mezzadri, Joseph Najnudel
Our model consists of two interacting spin glasses, and we conduct an extensive theoretical analysis of the complexity of the model's critical points using techniques from Random Matrix Theory.