Gauss-Newton Natural Gradient Descent for Shape Learning
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_ | 1866910021388861440 |
|---|---|
| author | King, James Berzins, Arturs Mishra, Siddhartha Zeinhofer, Marius |
| author_facet | King, James Berzins, Arturs Mishra, Siddhartha Zeinhofer, Marius |
| contents | We explore the use of the Gauss-Newton method for optimization in shape learning, including implicit neural surfaces and geometry-informed neural networks. The method addresses key challenges in shape learning, such as the ill-conditioning of the underlying differential constraints and the mismatch between the optimization problem in parameter space and the function space where the problem is naturally posed. This leads to significantly faster and more stable convergence than standard first-order methods, while also requiring far fewer iterations. Experiments across benchmark shape optimization tasks demonstrate that the Gauss-Newton method consistently improves both training speed and final solution accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00099 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Gauss-Newton Natural Gradient Descent for Shape Learning King, James Berzins, Arturs Mishra, Siddhartha Zeinhofer, Marius Machine Learning Optimization and Control We explore the use of the Gauss-Newton method for optimization in shape learning, including implicit neural surfaces and geometry-informed neural networks. The method addresses key challenges in shape learning, such as the ill-conditioning of the underlying differential constraints and the mismatch between the optimization problem in parameter space and the function space where the problem is naturally posed. This leads to significantly faster and more stable convergence than standard first-order methods, while also requiring far fewer iterations. Experiments across benchmark shape optimization tasks demonstrate that the Gauss-Newton method consistently improves both training speed and final solution accuracy. |
| title | Gauss-Newton Natural Gradient Descent for Shape Learning |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2602.00099 |