AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation

Jianlong Chen, Zhiming Zhou

ICLR 2026 · Optimization › Implicit bias and generalization · approach: Sharpness-aware minimization theory · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace SAM gradient with explicit direction estimate (XSAM)SAM · CIFAR-100 ResNet-18accuracy: 80.93 -> 81.24Improved
replace SAM gradient with explicit direction estimate (XSAM)SAM · Tiny-ImageNet VGG-11accuracy: 51.96 -> 52.58Improved
replace SAM gradient with explicit direction estimate (XSAM)SAM · ImageNet ResNet-50accuracy: 77.04 -> 77.22Improved
replace SAM gradient with explicit direction estimate (XSAM)SAM · IWSLT2014 TransformerBLEU: 35.30 -> 35.63Improved
replace SAM gradient with explicit direction estimate (XSAM)SAM · CIFAR-100 ViT-Tiaccuracy: 67.80 -> 68.32Improved
add single-step ascent gradient (SAM) over SGDSGD · CIFAR-100 ResNet-18accuracy: 78.55 -> 80.93Improved
increase ascent steps from k=1 to k=4 (ablation)SAM · CIFAR-100 ResNet-18accuracy: 80.93 -> 80.65Hurt
increase ascent steps from k=1 to k=4 (ablation)XSAM · CIFAR-100 ResNet-18accuracy: 81.27 -> 81.37Improved
increase ascent steps from k=1 to k=2 (ablation)MSAM · CIFAR-100 ResNet-18accuracy: 80.93 -> 81.18Improved
add initial gradient g0 to multi-step sum (MSAM+ vs MSAM) (ablation)MSAM · CIFAR-100 ResNet-18 k=2accuracy: 81.18 -> 80.86Hurt
add initial gradient g0 (LSAM+ vs LSAM) (ablation)LSAM · CIFAR-100 ResNet-18 k=4accuracy: 80.74 -> 80.41Hurt
update alpha* at different frequencies (ablation)XSAM · CIFAR-100accuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy