AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Random Sharpness-Aware Minimization

Yong Liu, Siqi Mai, Minhao Cheng, Xiangning Chen, Cho-Jui Hsieh, Yang You

NeurIPS 2022 · Optimization › Implicit bias and generalization · approach: Sharpness-aware minimization theory · 5 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
add random Gaussian initialization to SAM inner ascent (R-SAM)SAM / WRN-28-10 · CIFAR-10accuracy: 97.3 -> 97.5Improved
add random initialization to SAM (R-SAM)SAM / ResNet-18 · CIFAR-10accuracy: 96.4±0.2 -> 96.5±0.1Improved
add random initialization to SAM (R-SAM)SAM / ResNet-50 · CIFAR-100accuracy: 83.3% to 84.0%Improved
add random initialization to SAM (R-SAM)SAM / WRN-28-10 · CIFAR-100accuracy: 84.6% to 85.2%Improved
use SAM instead of SGD+MSGD+M / WRN-28-10 · CIFAR-10accuracy: 96.5% to 97.3%Improved
use SAM instead of AdamWAdamW / ViT-B-16 · ImageNet-1kaccuracy: 74.7% (AdamW) to 79.8% (SAM)Improved
add random initialization to SAM (R-SAM)SAM / ViT-B-16 · ImageNet-1kaccuracy: 79.8% (vanilla SAM) to 80.7%Improved
add random initialization to SAM (R-SAM)SAM / ViT-S-16 · ImageNet-1kaccuracy: 77.9% (vanilla SAM) to 78.7%Improved
add mixup augmentationAdamW / ViT-B-16 · ImageNet-1kaccuracy: 74.7% to 75.7%Improved
add mixup augmentationSAM / ViT-B-16 · ImageNet-1kaccuracy: 79.8% to 80.4%Improved
add R-SAM on top of SAM with mixupSAM / ViT-B-16 · ImageNet-1kaccuracy: 80.4% to 81.1%Improved
add RandAug on top of mixup (ablation)R-SAM / ViT-B-16 · ImageNet-1kaccuracy: 81.1 -> 81.6Improved

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