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

• URL: http://arxiv.org/abs/2605.10183v1
• Date: Mon, 11 May 2026 08:34:36 GMT
• Title: Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization
• Abstract summary: Loss-Equated SAM (LE-SAM) is a generalization of Sharpness-Aware Minimization (SAM) that removes gradient-norm-dominated learning signals and shifts optimization toward curvature-dominated terms.<n>Le-SAM consistently outperforms SAM and even its variants, achieving the state-of-the-art performance.
• Score: 7.865097630039961
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations [1.7073691799016324]
  Sharpness-Aware Minimization (SAM) was proposed as a training strategy that enhances generalization.<n>SAM suffers from its twice computational cost due to its core algorithm requiring an extra gradient during the perturbation step.<n>We introduce Exponential Moving Average Sharpness-Aware Minimization (EMASAM), a computationally efficient variant of SAM.
  arXiv  Detail & Related papers  (2026-08-15T08:10:31Z)
• Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization [11.183574804029165]
  GEAR-SAM maintains an exponential moving average (EMA) of squared block gradients as a lightweight, curvature-related sensitivity signal.<n>Experiments on image classification, transfer learning, noisy-label learning, and partition studies demonstrate improved generalization and robustness across architectures and tasks.
  arXiv  Detail & Related papers  (2026-07-17T06:59:02Z)
• LightSAM: Parameter-Agnostic Sharpness-Aware Minimization [92.17866492331524]
  Sharpness-Aware Minimization (SAM) enhances the ability of the machine learning model by exploring the flat minima landscape through weight perturbations.<n>SAM introduces an additional hyper- parameter, the perturbation radius, which causes the sensitivity of SAM to it.<n>In this paper, we propose the algorithm LightSAM which sets the perturbation radius and learning rate of SAM adaptively.
  arXiv  Detail & Related papers  (2025-05-30T09:28:38Z)
• Enhancing Sharpness-Aware Minimization by Learning Perturbation Radius [6.78775404181577]
  We propose a bilevel optimization framework called LEarning the perTurbation radiuS to learn the perturbation radius for sharpness-aware minimization algorithms. Experimental results on various architectures and benchmark datasets in computer vision and natural language processing demonstrate the effectiveness of the proposed LETS method.
  arXiv  Detail & Related papers  (2024-08-15T15:40:57Z)
• Friendly Sharpness-Aware Minimization [62.57515991835801]
  Sharpness-Aware Minimization (SAM) has been instrumental in improving deep neural network training by minimizing both training loss and loss sharpness. We investigate the key role of batch-specific gradient noise within the adversarial perturbation, i.e., the current minibatch gradient. By decomposing the adversarial gradient noise components, we discover that relying solely on the full gradient degrades generalization while excluding it leads to improved performance.
  arXiv  Detail & Related papers  (2024-03-19T01:39:33Z)
• Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy [12.050160495730381]
  sharpness-aware generalization (SAM) has attracted much attention because of its surprising effectiveness in improving performance. We propose a simple renormalization strategy, dubbed Stable SAM (SSAM), so that the gradient norm of the descent step maintains the same as that of the ascent step. Our strategy is easy to implement and flexible enough to integrate with SAM and its variants, almost at no computational cost.
  arXiv  Detail & Related papers  (2024-01-14T10:53:36Z)
• Enhancing Sharpness-Aware Optimization Through Variance Suppression [48.908966673827734]
  This work embraces the geometry of the loss function, where neighborhoods of 'flat minima' heighten generalization ability. It seeks 'flat valleys' by minimizing the maximum loss caused by an adversary perturbing parameters within the neighborhood. Although critical to account for sharpness of the loss function, such an 'over-friendly adversary' can curtail the outmost level of generalization.
  arXiv  Detail & Related papers  (2023-09-27T13:18:23Z)
• Normalization Layers Are All That Sharpness-Aware Minimization Needs [53.799769473526275]
  Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima. We show that perturbing only the affine normalization parameters (typically comprising 0.1% of the total parameters) in the adversarial step of SAM can outperform perturbing all of the parameters.
  arXiv  Detail & Related papers  (2023-06-07T08:05:46Z)
• Surrogate Gap Minimization Improves Sharpness-Aware Training [52.58252223573646]
  Surrogate textbfGap Guided textbfSharpness-textbfAware textbfMinimization (GSAM) is a novel improvement over Sharpness-Aware Minimization (SAM) with negligible computation overhead. GSAM seeks a region with both small loss (by step 1) and low sharpness (by step 2), giving rise to a model with high generalization capabilities.
  arXiv  Detail & Related papers  (2022-03-15T16:57:59Z)
• Efficient Sharpness-aware Minimization for Improved Training of Neural Networks [146.2011175973769]
  This paper proposes Efficient Sharpness Aware Minimizer (M) which boosts SAM s efficiency at no cost to its generalization performance. M includes two novel and efficient training strategies-StochasticWeight Perturbation and Sharpness-Sensitive Data Selection. We show, via extensive experiments on the CIFAR and ImageNet datasets, that ESAM enhances the efficiency over SAM from requiring 100% extra computations to 40% vis-a-vis bases.
  arXiv  Detail & Related papers  (2021-10-07T02:20:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.