27–31 May 2024
ECT*
Europe/Rome timezone

Learning and (not quite) random matrix theory

31 May 2024, 11:30
45m
Aula Renzo Leonardi (ECT*)

Aula Renzo Leonardi

ECT*

Strada delle Tabarelle 286, I-38123 Villazzano (Trento)

Speaker

Gert Aarts (Swansea University)

Description

We demonstrate that the update of weight matrices in learning algorithms has many features of random matrix theory, allowing for a stochastic Coulomb gas description in a modified Gaussian orthogonal ensemble. We relate the level of stochasticity to the ratio of the learning rate and the batch size. We identify the Wigner surmise and Wigner semicircle explicitly in a teacher-student model and in the (near-)solvable case of the Gaussian Restricted Boltzmann Machine.

Primary authors

Gert Aarts (Swansea University) Mr Chanju Park (Swansea University) Biagio Lucini (Swansea University)

Presentation materials

There are no materials yet.