Data Augmentation and Regularization for Learning Group Equivariance
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916606368546816 |
|---|---|
| author | Nordenfors, Oskar Flinth, Axel |
| author_facet | Nordenfors, Oskar Flinth, Axel |
| contents | In many machine learning tasks, known symmetries can be used as an inductive bias to improve model performance. In this paper, we consider learning group equivariance through training with data augmentation. We summarize results from a previous paper of our own, and extend the results to show that equivariance of the trained model can be achieved through training on augmented data in tandem with regularization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06547 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data Augmentation and Regularization for Learning Group Equivariance Nordenfors, Oskar Flinth, Axel Machine Learning Optimization and Control 68T07, 20C35, 37N40 In many machine learning tasks, known symmetries can be used as an inductive bias to improve model performance. In this paper, we consider learning group equivariance through training with data augmentation. We summarize results from a previous paper of our own, and extend the results to show that equivariance of the trained model can be achieved through training on augmented data in tandem with regularization. |
| title | Data Augmentation and Regularization for Learning Group Equivariance |
| topic | Machine Learning Optimization and Control 68T07, 20C35, 37N40 |
| url | https://arxiv.org/abs/2502.06547 |