Layer-wise Adaptive Gradient Norm Penalizing Method for Efficient and Accurate Deep Learning

• URL: http://arxiv.org/abs/2503.14205v1
• Date: Tue, 18 Mar 2025 12:30:57 GMT
• Title: Layer-wise Adaptive Gradient Norm Penalizing Method for Efficient and Accurate Deep Learning
• Authors: Sunwoo Lee,
• Abstract summary: Sharpness-aware minimization (SAM) is known to improve the generalization performance of neural networks.<n>SAM is not widely used in real-world applications yet due to its expensive model perturbation cost.<n>We propose a lightweight layer-wise gradient norm penalizing method that tackles the expensive computational cost of SAM while maintaining its superior generalization performance.
• Score: 7.6677237955415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sharpness-aware minimization (SAM) is known to improve the generalization performance of neural networks. However, it is not widely used in real-world applications yet due to its expensive model perturbation cost. A few variants of SAM have been proposed to tackle such an issue, but they commonly do not alleviate the cost noticeably. In this paper, we propose a lightweight layer-wise gradient norm penalizing method that tackles the expensive computational cost of SAM while maintaining its superior generalization performance. Our study empirically proves that the gradient norm of the whole model can be effectively suppressed by penalizing the gradient norm of only a few critical layers. We also theoretically show that such a partial model perturbation does not harm the convergence rate of SAM, allowing them to be safely adapted in real-world applications. To demonstrate the efficacy of the proposed method, we perform extensive experiments comparing the proposed method to mini-batch SGD and the conventional SAM using representative computer vision and language modeling benchmarks.

Related papers

• Sparse Layer Sharpness-Aware Minimization for Efficient Fine-Tuning [52.63618112418439]
  Sharpness-aware computation (SAM) seeks the minima with a flat loss landscape to improve the generalization performance in machine learning tasks, including fine-tuning.<n>We propose an approach SL-SAM to break this bottleneck by introducing the sparse technique to layers.
  arXiv  Detail & Related papers  (2026-02-10T04:05:43Z)
• Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models [21.52081811249999]
  We analyze the norm dynamics of Sharpness-Aware Minimization (SAM) in general tensorized models.<n>We show that SAM's implicit control of Norm Deviation is governed by the covariance between core norms and their gradient magnitudes.<n>Motivated by these findings, we propose a simple yet effective method, emphDeviation-Aware Scaling (DAS), which explicitly mimics this regularization behavior by scaling core norms in a data-adaptive manner.
  arXiv  Detail & Related papers  (2025-08-14T08:17:34Z)
• 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)
• Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization [21.747141953620698]
  Deep neural networks have been increasingly used in safety-critical applications such as medical diagnosis and autonomous driving.<n>Many studies suggest that they are prone to being poorly calibrated and have a propensity for overconfidence, which may have disastrous consequences.<n>We show that the recently proposed sharpness-aware minimization (SAM) counteracts this tendency towards overconfidence.<n>We propose a variant of SAM, coined as CSAM, to ameliorate model calibration.
  arXiv  Detail & Related papers  (2025-05-29T09:55:29Z)
• Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification [113.6840565194525]
  Real-world datasets often follow a long-tailed distribution, making generalization to tail classes difficult.<n>Recent methods resorted to long-tail variants of Sharpness-Aware Minimization (SAM) to improve generalization by flattening the loss landscape.<n>We introduce Focal-SAM, which assigns different penalties to class-wise, achieving fine-grained control without extra backpropagations.
  arXiv  Detail & Related papers  (2025-05-03T03:01:28Z)
• Asynchronous Sharpness-Aware Minimization For Fast and Accurate Deep Learning [5.77502465665279]
  Sharpness-Aware Minimization (SAM) is an optimization method that improves generalization performance of machine learning models. Despite its superior generalization, SAM has not been actively used in real-world applications due to its expensive computational cost. We propose a novel asynchronous-parallel SAM which achieves nearly the same gradient normizing effect like the original SAM while breaking the data dependency between the model perturbation and the model update.
  arXiv  Detail & Related papers  (2025-03-14T07:34:39Z)
• LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM [13.180761892449736]
  We study robust parameter-efficient fine-tuning (PEFT) techniques for large-language models (LLMs)<n>We present a new highly computationally efficient framework called AdaZo-SAM, combining Adam and Sharpness-Aware Minimization (SAM)<n>We also design a low-rank gradient optimization method named LORENZA, which is a memory-efficient version of AdaZo-SAM.
  arXiv  Detail & Related papers  (2025-02-26T21:30:34Z)
• GCSAM: Gradient Centralized Sharpness Aware Minimization [45.05109291721135]
  Sharpness-Aware Minimization (SAM) has emerged as an effective optimization technique for reducing the sharpness of the loss landscape.<n>We propose Gradient-Sharpness-Aware Minimization (GCSAM), which incorporates Gradient Centralization (GC) to stabilize and accelerate convergence.<n>GCSAM consistently outperforms SAM and the Adam in terms of generalization and computational efficiency.
  arXiv  Detail & Related papers  (2025-01-20T16:42:31Z)
• Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning [63.55145330447408]
  We propose a novel textbfSelf-textbfPerceptinon textbfTuning (textbfSPT) method for anomaly segmentation.<n>The SPT method incorporates a self-drafting tuning strategy, which generates an initial coarse draft of the anomaly mask, followed by a refinement process.
  arXiv  Detail & Related papers  (2024-11-26T08:33:25Z)
• μP$^2$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling [49.25546155981064]
  We study the infinite-width limit of neural networks trained with Sharpness Aware Minimization (SAM)<n>Our findings reveal that the dynamics of standard SAM effectively reduce to applying SAM solely in the last layer in wide neural networks.<n>In contrast, we identify a stable parameterization with layerwise scaling, which we call $textitMaximal Update and Perturbation $ ($mu$P$2$), that ensures all layers are both feature learning and effectively perturbed in the limit.
  arXiv  Detail & Related papers  (2024-10-31T16:32:04Z)
• 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)
• Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer [158.2634766682187]
  Deep neural networks often suffer from poor generalization due to complex and non- unstructured loss landscapes. SharpnessAware Minimization (SAM) is a popular solution that smooths the loss by minimizing the change of landscape when adding a perturbation. In this paper, we propose Sparse SAM (SSAM), an efficient and effective training scheme that achieves perturbation by a binary mask.
  arXiv  Detail & Related papers  (2023-06-30T09:33:41Z)
• 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)
• Sharpness-Aware Training for Free [163.1248341911413]
  SharpnessAware Minimization (SAM) has shown that minimizing a sharpness measure, which reflects the geometry of the loss landscape, can significantly reduce the generalization error. Sharpness-Aware Training Free (SAF) mitigates the sharp landscape at almost zero computational cost over the base. SAF ensures the convergence to a flat minimum with improved capabilities.
  arXiv  Detail & Related papers  (2022-05-27T16:32:43Z)
• 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.