Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.29262 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912990600626176 |
|---|---|
| author | Zhang, Junjie Shen, Zhen Xiong, Gang Dong, Xisong |
| author_facet | Zhang, Junjie Shen, Zhen Xiong, Gang Dong, Xisong |
| contents | Grokking in modular arithmetic has established itself as the quintessential fruit fly experiment, serving as a critical domain for investigating the mechanistic origins of model generalization. Despite its significance, existing research remains narrowly focused on specific local circuits or optimization tuning, largely overlooking the global structural evolution that fundamentally drives this phenomenon. We propose that grokking originates from a spontaneous simplification of internal model structures governed by the principle of parsimony. We integrate causal, spectral, and algorithmic complexity measures alongside Singular Learning Theory to reveal that the transition from memorization to generalization corresponds to the physical collapse of redundant manifolds and deep information compression, offering a novel perspective for understanding the mechanisms of model overfitting and generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29262 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Grokking From Abstraction to Intelligence Zhang, Junjie Shen, Zhen Xiong, Gang Dong, Xisong Artificial Intelligence Grokking in modular arithmetic has established itself as the quintessential fruit fly experiment, serving as a critical domain for investigating the mechanistic origins of model generalization. Despite its significance, existing research remains narrowly focused on specific local circuits or optimization tuning, largely overlooking the global structural evolution that fundamentally drives this phenomenon. We propose that grokking originates from a spontaneous simplification of internal model structures governed by the principle of parsimony. We integrate causal, spectral, and algorithmic complexity measures alongside Singular Learning Theory to reveal that the transition from memorization to generalization corresponds to the physical collapse of redundant manifolds and deep information compression, offering a novel perspective for understanding the mechanisms of model overfitting and generalization. |
| title | Grokking From Abstraction to Intelligence |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.29262 |