LAMB

2000년 도입 · 논문 199편에서 사용

LAMB is a a layerwise adaptive large batch optimization technique. It provides a strategy for adapting the learning rate in large batch settings. LAMB uses Adam as the base algorithm and then forms an update as: $$r\_{t} = \frac{m\_{t}}{\sqrt{v\_{t}} + \epsilon}$$ $$x\_{t+1}^{\left(i\right)} = x\_{t}^{\left(i\right)} - \eta\_{t}\frac{\phi\left(|| x\_{t}^{\left(i\right)} ||\right)}{|| m\_{t}^{\left(i\right)} || }\left(r\_{t}^{\left(i\right)}+\lambda{x\_{t}^{\left(i\right)}}\right) $$ Unlike LARS, the adaptivity of LAMB is two-fold: (i) per dimension normalization with respect to the square root of the second moment used in Adam and (ii) layerwise normalization obtained due to layerwise adaptivity.

출처: Large Batch Optimization for Deep Learning: Training BERT in 76 minutes

소개 논문: Large Batch Optimization for Deep Learning: Training BERT in 76 minutes