Which Algorithms Have Tight Generalization Bounds?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917793557905408 |
|---|---|
| author | Gastpar, Michael Nachum, Ido Shafer, Jonathan Weinberger, Thomas |
| author_facet | Gastpar, Michael Nachum, Ido Shafer, Jonathan Weinberger, Thomas |
| contents | We study which machine learning algorithms have tight generalization bounds. First, we present conditions that preclude the existence of tight generalization bounds. Specifically, we show that algorithms that have certain inductive biases that cause them to be unstable do not admit tight generalization bounds. Next, we show that algorithms that are sufficiently stable do have tight generalization bounds. We conclude with a simple characterization that relates the existence of tight generalization bounds to the conditional variance of the algorithm's loss. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01969 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Which Algorithms Have Tight Generalization Bounds? Gastpar, Michael Nachum, Ido Shafer, Jonathan Weinberger, Thomas Machine Learning We study which machine learning algorithms have tight generalization bounds. First, we present conditions that preclude the existence of tight generalization bounds. Specifically, we show that algorithms that have certain inductive biases that cause them to be unstable do not admit tight generalization bounds. Next, we show that algorithms that are sufficiently stable do have tight generalization bounds. We conclude with a simple characterization that relates the existence of tight generalization bounds to the conditional variance of the algorithm's loss. |
| title | Which Algorithms Have Tight Generalization Bounds? |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.01969 |