Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm
Wenzhi Zhong, Edward Milsom, Michael Murray
cs.LG, stat.ML
Submitted: 2026-07-28
Code: https://github.com/huggingface/pytorch-image-models
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Towards Understanding Sharpness-Aware Minimization
- Momentum-SAM: Sharpness Aware Minimization without Computational Overhead
- Are we done with ImageNet?
- Better plain ViT baselines for ImageNet-1k
- When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- Escaping the Big Data Paradigm with Compact Transformers
- Deep Residual Learning for Image Recognition
- The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization
- Kimi K2: Open Agentic Intelligence
- Muon is Scalable for LLM Training
- Isambard-AI: a leadership class supercomputer optimised specifically for Artificial Intelligence
- Training Deep Learning Models with Norm-Constrained LMOs
- Arcee Trinity Large Technical Report
- How Does Sharpness-Aware Minimization Minimize Sharpness?
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks