Cooper: A Library for Constrained Optimization in Deep Learning
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_ | 1866910901557264384 |
|---|---|
| author | Gallego-Posada, Jose Ramirez, Juan Hashemizadeh, Meraj Lacoste-Julien, Simon |
| author_facet | Gallego-Posada, Jose Ramirez, Juan Hashemizadeh, Meraj Lacoste-Julien, Simon |
| contents | Cooper is an open-source package for solving constrained optimization problems involving deep learning models. Cooper implements several Lagrangian-based first-order update schemes, making it easy to combine constrained optimization algorithms with high-level features of PyTorch such as automatic differentiation, and specialized deep learning architectures and optimizers. Although Cooper is specifically designed for deep learning applications where gradients are estimated based on mini-batches, it is suitable for general non-convex continuous constrained optimization. Cooper's source code is available at https://github.com/cooper-org/cooper. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01212 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cooper: A Library for Constrained Optimization in Deep Learning Gallego-Posada, Jose Ramirez, Juan Hashemizadeh, Meraj Lacoste-Julien, Simon Machine Learning Mathematical Software Cooper is an open-source package for solving constrained optimization problems involving deep learning models. Cooper implements several Lagrangian-based first-order update schemes, making it easy to combine constrained optimization algorithms with high-level features of PyTorch such as automatic differentiation, and specialized deep learning architectures and optimizers. Although Cooper is specifically designed for deep learning applications where gradients are estimated based on mini-batches, it is suitable for general non-convex continuous constrained optimization. Cooper's source code is available at https://github.com/cooper-org/cooper. |
| title | Cooper: A Library for Constrained Optimization in Deep Learning |
| topic | Machine Learning Mathematical Software |
| url | https://arxiv.org/abs/2504.01212 |