Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2412.18624 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _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 |