English

Generalization Error of $f$-Divergence Stabilized Algorithms via Duality

Machine Learning 2025-02-21 v1 Machine Learning

Abstract

The solution to empirical risk minimization with ff-divergence regularization (ERM-ffDR) is extended to constrained optimization problems, establishing conditions for equivalence between the solution and constraints. A dual formulation of ERM-ffDR is introduced, providing a computationally efficient method to derive the normalization function of the ERM-ffDR solution. This dual approach leverages the Legendre-Fenchel transform and the implicit function theorem, enabling explicit characterizations of the generalization error for general algorithms under mild conditions, and another for ERM-ffDR solutions.

Keywords

Cite

@article{arxiv.2502.14544,
  title  = {Generalization Error of $f$-Divergence Stabilized Algorithms via Duality},
  author = {Francisco Daunas and Iñaki Esnaola and Samir M. Perlaza and Gholamali Aminian},
  journal= {arXiv preprint arXiv:2502.14544},
  year   = {2025}
}

Comments

This is new work for ISIT2025. arXiv admin note: text overlap with arXiv:2402.00501

R2 v1 2026-06-28T21:51:19.873Z