Explaining f-Divergence-Based Regularization via Local Curvature and Sharpness-Aware Minimization

2026-09-08

AI Summary

该研究通过局部曲率分析，探讨了基于f-散度的正则化与锐度感知最小化(SAM)之间的关系，并提出了一种新的输入空间扰动框架。

Abstract

Divergence-based regularization and Sharpness-Aware Minimization (SAM) are two prominent approaches for improving generalization in deep learning, both motivated by robustness to perturbations. However, their relationship has remained largely unexplored. Building on classical second-order expansions of $f$-divergences, we show that the two methods are locally consistent under parameter-space perturbations: both induce curvature-sensitive penalties, with divergence regularization yielding a Fisher-weighted quadratic form and SAM penalizing sharpness through the dominant Hessian eigenvalue. For negative log-likelihood objectives with exponential-family output distributions, this correspondence becomes especially transparent, since the Fisher and Gauss-Newton matrices coincide. We further show that the same local geometric perspective extends to input-space perturbations, where divergence-based regularization is defined through transformations of the input. In this setting, the regularizer induces a pullback quadratic form on the input space, providing a more general perturbation framework than standard SAM while preserving the same local sensitivity interpretation. To validate the analysis empirically, we use the asymmetric $α$-skew Jensen-Shannon divergence (JSD) family as a controlled testbed. Its local curvature coefficient scales as $α(1-α)$ and is maximized at the symmetric point $α=\tfrac12$, which recovers the standard JSD. Loss-landscape visualizations in the input-perturbation regime show that stronger induced curvature penalization is associated with flatter local minima. Experiments on four benchmark datasets further demonstrate that both accuracy and negative log-likelihood are consistently best near this regime of maximal curvature penalization.

Problem

• f-Divergence
• Regularization
• Sharpness-Aware Minimization
• Generalization
• Perturbations

Innovation

• f-Divergence
• Sharpness-Aware Minimization (SAM)
• Local Curvature
• Fisher Information
• Perturbation Robustness