تقرير
Model Generalization: A Sharpness Aware Optimization Perspective
العنوان: | Model Generalization: A Sharpness Aware Optimization Perspective |
---|---|
المؤلفون: | Coldenhoff, Jozef Marus, Li, Chengkun, Zhu, Yurui |
سنة النشر: | 2022 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence |
الوصف: | 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. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2208.06915 |
رقم الأكسشن: | edsarx.2208.06915 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!