Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.16427 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929666893283328 |
|---|---|
| author | Aarts, Gert Lucini, Biagio Park, Chanju |
| author_facet | Aarts, Gert Lucini, Biagio Park, Chanju |
| contents | We demonstrate that the update of weight matrices in learning algorithms can be described in the framework of Dyson Brownian motion, thereby inheriting many features of random matrix theory. We relate the level of stochasticity to the ratio of the learning rate and the mini-batch size, providing more robust evidence to a previously conjectured scaling relationship. We discuss universal and non-universal features in the resulting Coulomb gas distribution and 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16427 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Stochastic weight matrix dynamics during learning and Dyson Brownian motion Aarts, Gert Lucini, Biagio Park, Chanju Disordered Systems and Neural Networks Machine Learning High Energy Physics - Lattice We demonstrate that the update of weight matrices in learning algorithms can be described in the framework of Dyson Brownian motion, thereby inheriting many features of random matrix theory. We relate the level of stochasticity to the ratio of the learning rate and the mini-batch size, providing more robust evidence to a previously conjectured scaling relationship. We discuss universal and non-universal features in the resulting Coulomb gas distribution and 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. |
| title | Stochastic weight matrix dynamics during learning and Dyson Brownian motion |
| topic | Disordered Systems and Neural Networks Machine Learning High Energy Physics - Lattice |
| url | https://arxiv.org/abs/2407.16427 |