YanaiEliyahu/AdasOptimizer
ADAS is short for Adaptive Step Size, it's an optimizer that unlike other optimizers that just normalize the derivative, it fine-tunes the step size, truly making step size scheduling obsolete, achieving state-of-the-art training performance
C++MIT
Issues
- 3
- 2
- 7
Pytorch
#1 opened by FilipAndersson245