arXiv Computer Vision September 15, 2026 By Shiryu Ueno, Yoshikazu Hayashi, Kunihito Kato

Sparsity-Adaptive Sharpness-Aware Minimization

Read the original on arXiv Computer Vision →

The paper introduces Sparsity-Adaptive Sharpness-Aware Minimization (SA‑SAM), a method that adjusts the perturbation radius in sharpness-aware training to remain consistent as model sparsity increases. It also evaluates a Magnitude‑Weighted Hessian (MWH) importance metric derived from second‑order analysis. Experiments on CIFAR‑10‑C, CIFAR‑100‑C, and ImageNet‑100‑C show that SA‑SAM improves corruption robustness at 80–90% sparsity while maintaining clean accuracy, and the study reports inference throughput at deployment‑relevant sparsity levels.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

efficiency

arXiv Machine Learning

Aug 10

The Sparsity Whisperer

arXiv:2608. 06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs.

By Linghao Kong, Inimai Subramanian, Micah Adler, Dan Alistarh, Dan Gutfreund, Nir Shavit

llms efficiency multimodal

arXiv Machine Learning

Jul 17

Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance

arXiv:2607. 14466v1 Announce Type: new Abstract: Noise injection is a well-known technique in stochastic optimization.

By Matt L. Wiemann, Peter Melchior, Andrew K. Saydjari

safety

arXiv Machine Learning

Jul 8

Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning

arXiv:2607. 06151v1 Announce Type: new Abstract: Generalization remains a pivotal challenge in deep learning, where traditional optimizers like Stochastic Gradient Descent (SGD) often converge to sharp minima, leading to overfitting and reduced performance on unseen data.

By Yao Fu, Chunxia Zhang, Junmin Liu, Yihang Jin, Haishan Ye, Yuanao Yang

benchmarks

arXiv Machine Learning

Sep 1

MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models

arXiv:2604.13287v2 Announce Type: replace Abstract: Weight pruning is a common technique for compressing large neural networks. We focus on the challenging post-training one-shot setting, where a pre...

By Gabriel Afriat, Xiang Meng, Shibal Ibrahim, Hussein Hazimeh, Rahul Mazumder

llms efficiency benchmarks

arXiv Machine Learning

Jun 2

A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs

arXiv:2606. 02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment.

By Nicolas Stalder, Benjamin F. Grewe, Matteo Saponati, Pau Vilimelis Aceituno

benchmarks safety

arXiv Machine Learning

Aug 18

EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations

arXiv:2608. 15105v1 Announce Type: new Abstract: Recent progress in optimization research has highlighted the sharpness of the loss landscape as a key factor in narrowing the generalization gap.

By Tanapat Ratchatorn, Masayuki Tanaka

One email a morning, machine-written

Related stories

The Sparsity Whisperer

Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance

Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning

MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models

A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs

EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations