Model Generalization: A Sharpness Aware Optimization Perspective
This work addresses model generalization for machine learning practitioners, but it is incremental as it validates existing methods without major innovations.
The paper investigated Sharpness-Aware Minimization (SAM) and adaptive SAM (ASAM) to improve model generalization, finding that these techniques enhance generalization ability, with ASAM showing potential on un-normalized data.
Sharpness-Aware Minimization (SAM) and adaptive sharpness-aware minimization (ASAM) aim to improve the model generalization. And in this project, we proposed three experiments to valid their generalization from the sharpness aware perspective. And our experiments show that sharpness aware-based optimization techniques could help to provide models with strong generalization ability. Our experiments also show that ASAM could improve the generalization performance on un-normalized data, but further research is needed to confirm this.