Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.20995 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915584611975168 |
|---|---|
| author | Boero, Ignacio Hounie, Ignacio Ribeiro, Alejandro |
| author_facet | Boero, Ignacio Hounie, Ignacio Ribeiro, Alejandro |
| contents | Despite the non-convexity of most modern machine learning parameterizations, Lagrangian duality has become a popular tool for addressing constrained learning problems. We revisit Augmented Lagrangian methods, which aim to mitigate the duality gap in non-convex settings while requiring only minimal modifications, and have remained comparably unexplored in constrained learning settings. We establish strong duality results under mild conditions, prove convergence of dual ascent algorithms to feasible and optimal primal solutions, and provide PAC-style generalization guarantees. Finally, we demonstrate its effectiveness on fairness constrained classification tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20995 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AL-CoLe: Augmented Lagrangian for Constrained Learning Boero, Ignacio Hounie, Ignacio Ribeiro, Alejandro Machine Learning Signal Processing Despite the non-convexity of most modern machine learning parameterizations, Lagrangian duality has become a popular tool for addressing constrained learning problems. We revisit Augmented Lagrangian methods, which aim to mitigate the duality gap in non-convex settings while requiring only minimal modifications, and have remained comparably unexplored in constrained learning settings. We establish strong duality results under mild conditions, prove convergence of dual ascent algorithms to feasible and optimal primal solutions, and provide PAC-style generalization guarantees. Finally, we demonstrate its effectiveness on fairness constrained classification tasks. |
| title | AL-CoLe: Augmented Lagrangian for Constrained Learning |
| topic | Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2510.20995 |