Algorithmresearch
Sharpness-aware minimization
Also called SAM.
Minimizes the loss in a neighbourhood of the weights, seeking flat minima that generalize better.
Minimizes the loss in a neighbourhood of the weights, seeking flat minima that generalize better.
About this page
The build computes these levels from the evidence in the repository. Each row says what the next level needs. Read what the levels mean.
| Ladder | Level | What the next level needs |
|---|---|---|
| Human proof | H0 no proof |
|
| Lean | L0 no Lean part |
|
| Visual | V0 none |
|
| Writing | W0 stub |
|
Tag GSR20V Edit this page History Report an error