Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912944746397696 |
|---|---|
| author | Alrashdi, Ayed M. Dhifallah, Oussama Sifaou, Houssem |
| author_facet | Alrashdi, Ayed M. Dhifallah, Oussama Sifaou, Houssem |
| contents | Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge in multi--task learning is identifying formulations capable of uncovering the common information shared between different but related tasks. This paper provides a precise asymptotic analysis of a popular multi--task formulation associated with misspecified perceptron learning models. The main contribution of this paper is to precisely determine the reasons behind the benefits gained from combining multiple related tasks. Specifically, we show that combining multiple tasks is asymptotically equivalent to a traditional formulation with additional regularization terms that help improve the generalization performance. Another contribution is to empirically study the impact of combining tasks on the generalization error. In particular, we empirically show that the combination of multiple tasks postpones the double descent phenomenon and can mitigate it asymptotically. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05060 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects Alrashdi, Ayed M. Dhifallah, Oussama Sifaou, Houssem Machine Learning Information Theory Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge in multi--task learning is identifying formulations capable of uncovering the common information shared between different but related tasks. This paper provides a precise asymptotic analysis of a popular multi--task formulation associated with misspecified perceptron learning models. The main contribution of this paper is to precisely determine the reasons behind the benefits gained from combining multiple related tasks. Specifically, we show that combining multiple tasks is asymptotically equivalent to a traditional formulation with additional regularization terms that help improve the generalization performance. Another contribution is to empirically study the impact of combining tasks on the generalization error. In particular, we empirically show that the combination of multiple tasks postpones the double descent phenomenon and can mitigate it asymptotically. |
| title | Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects |
| topic | Machine Learning Information Theory |
| url | https://arxiv.org/abs/2603.05060 |