Saved in:
Bibliographic Details
Main Authors: Boero, Ignacio, Hounie, Ignacio, Ribeiro, Alejandro
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