The Lion optimizer is discovered by symbolic program search. It is more memory-efficient than most adaptive optimizers as it only needs to momentum. The update of Lion is produced by the sign function.
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Federated Learning | 1 | 16.67% |
Quantization | 1 | 16.67% |
Handwritten Text Recognition | 1 | 16.67% |
Offline RL | 1 | 16.67% |
Image Classification | 1 | 16.67% |
Language Modelling | 1 | 16.67% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |