Manipulating Sparse Double Descent
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911760927162368 |
|---|---|
| author | Zhang, Ya Shi |
| author_facet | Zhang, Ya Shi |
| contents | This paper investigates the double descent phenomenon in two-layer neural networks, focusing on the role of L1 regularization and representation dimensions. It explores an alternative double descent phenomenon, named sparse double descent. The study emphasizes the complex relationship between model complexity, sparsity, and generalization, and suggests further research into more diverse models and datasets. The findings contribute to a deeper understanding of neural network training and optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10686 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Manipulating Sparse Double Descent Zhang, Ya Shi Machine Learning This paper investigates the double descent phenomenon in two-layer neural networks, focusing on the role of L1 regularization and representation dimensions. It explores an alternative double descent phenomenon, named sparse double descent. The study emphasizes the complex relationship between model complexity, sparsity, and generalization, and suggests further research into more diverse models and datasets. The findings contribute to a deeper understanding of neural network training and optimization. |
| title | Manipulating Sparse Double Descent |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2401.10686 |