cs.LGNov 14, 2026

Probing SAM Perturbations Through Statistical Replay

Authors: Ting Han, Jens Kleesiek, Michael Kamp

Organizations: TU Dortmund, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Germany · Institute for Artificial Intelligence in Medicine, UK Essen, Germany

Abstract

Sharpness Aware Minimization (SAM) updates model parameters using gradients evaluated at adversarially perturbed weights, but it remains unclear which aspects of this procedure are sufficient to reproduce its generalization behavior. In our ResNet 18 experiments on CIFAR 10, simple curvature regularizers based on the Hessian trace and largest eigenvalue remain below SAM in validation accuracy, motivating a direct examination of its perturbations. We introduce statistical replay, a diagnostic that summarizes perturbations from reference SAM trajectories using elementwise means and standard deviations over local windows and constructs new perturbations during independent SGD training. Pure replay uses only these summaries, whereas mixed replay adds isotropic Gaussian noise. Pure replay does not reproduce SAM's validation behavior, while mixed replay and pure isotropic perturbations can approach its validation performance at selected scales without reproducing its training dynamics. An equal radius random direction within SAM performs similarly to SGD, and source, temporal, and layer interventions further suggest that replay behavior depends on perturbation construction. Together, these preliminary results weaken several simple explanations of SAM while leaving an important part of its mechanism unexplained.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Aug 4, 2026

On the Implicit Flatness Bias of Sharpness-Aware Minimization: A Linear Stability Analysis with Quantitative Hyperparameter Bounds

Sharpness-Aware Minimization (SAM) improves generalization by seeking parameters whose loss is robust to local adversarial perturbations, but the quantitative mechanism underlying its implicit bias toward flat minima remains unclear. In particular, the perturbation radius ρρ is typically treated as an isolated tuning parameter, despite defining the neighborhood in which SAM measures sharpness. We analyze mini-batch SAM near an interpolating minimum through linear stability. Under local linearization and gradient-noise alignment assumptions, we prove that every linearly stable minimum satisfies λmax⁡≤bΓ/(2ρη2)3λ_{\max}\leq\sqrt[3]{bΓ/(2ρη^2)}, where λmax⁡λ_{\max} is the largest Hessian eigenvalue, bb is the batch size, ηη is the learning rate, and ΓΓ bounds the gradient norm. The bound quantitatively characterizes SAM's implicit flatness bias: holding the other quantities fixed, a smaller batch size, a larger learning rate, or a larger radius restricts linearly stable SAM to flatter minima. It also exposes a necessary trade-off: ρρ should be large enough to promote flatness, yet remain local enough to preserve the approximation and stable training. We validate this prediction in a controlled study of 900 models on CIFAR-100 with ResNet-18 and VGG-19, where increasing ρρ is consistently associated with a smaller largest Hessian eigenvalue across batch-size and learning-rate settings. Finally, we instantiate the analysis in Taylor-Locality Controlled SAM (TLC-SAM), which adjusts ρρ using the observed Taylor-approximation error and further reduces the top Hessian eigenvalue relative to fixed-radius SAM. Our results provide quantitative hyperparameter bounds and a stability--locality perspective for analyzing and designing SAM variants.
May 11, 2026

Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization

Sharpness-Aware Minimization (SAM) improves generalization by minimizing the worst-case loss within a fixed parameter-space radius neighborhood. SAM and its variants mainly rely on a first-order linearized surrogate, while flat minima are inherently a second-order (curvature) notion.We revisit this mismatch and propose Loss-Equated SAM (LE-SAM), which inverts the traditional SAM mechanism that fixed perturbation radius with a fixed loss-space budget,effectively removing gradient-norm-dominated learning signals and shifting optimization toward curvature-dominated terms. Extensive experiments across diverse benchmarks and tasks demonstrate the strong generalization ability of LESAM that consistently outperforms SAM and even its variants, achieving the state-of-the-art performance.
Oct 14, 2026

One Size Does Not Fit All: Curvature-Aware Adaptive Perturbation for SAM

Poor generalisation in deep neural networks is frequently associated with convergence to sharp minima. Sharpness-Aware Minimisation (SAM) improves generalisation of deep neural networks by minimising a combination of the training loss and the local sharpness of the loss landscape, biasing convergence towards flat minima. However, SAM relies on a fixed perturbation radius ρρ that ignores local curvature, leading to inefficient behaviour: the perturbation may be too small to escape poor basins defined by sharp local minima, or too large to allow convergence to solutions with good loss-sharpness tradeoff. We reinterpret ρρ as the intensity of the perturbation signal and propose Curvature-Aware Adaptive Perturbation for SAM (CAP-SAM), a geometry-aware method that modulates the perturbation radius based on a sharpness ratio, enabling a more effective search for robust minima on the loss landscape. We prove that CAP-SAM preserves the same convergence rate as standard SAM in non-convex stochastic settings. Extensive experiments indicate that our approach consistently outperforms SAM and its most prominent variants across diverse network architectures on CIFAR-10, CIFAR-100, and ImageNet.