How to explain grokking
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917129686614016 |
|---|---|
| author | Kozyrev, S. V. |
| author_facet | Kozyrev, S. V. |
| contents | Explanation of grokking (delayed generalization) in learning is given by modeling grokking by the stochastic gradient Langevin dynamics (Brownian motion) and applying the ideas of thermodynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18624 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | How to explain grokking Kozyrev, S. V. Statistical Mechanics Machine Learning Explanation of grokking (delayed generalization) in learning is given by modeling grokking by the stochastic gradient Langevin dynamics (Brownian motion) and applying the ideas of thermodynamics. |
| title | How to explain grokking |
| topic | Statistical Mechanics Machine Learning |
| url | https://arxiv.org/abs/2412.18624 |