Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer
Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of training loss when adding a perturbation to the weight. However, in...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 10 vom: 23. Sept., Seite 8538-8549
|
|---|
| 1. Verfasser: |
Mi, Peng
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Shen, Li,
Ren, Tianhe,
Zhou, Yiyi,
Xu, Tianshuo,
Sun, Xiaoshuai,
Liu, Tongliang,
Ji, Rongrong,
Tao, Dacheng |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2025
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|