QHM

2000년 도입 · 논문 2편에서 사용

Quasi-Hyperbolic Momentum (QHM) is a stochastic optimization technique that alters momentum SGD with a momentum step, averaging an SGD step with a momentum step: $$ g\_{t+1} = \beta{g\_{t}} + \left(1-\beta\right)\cdot{\nabla}\hat{L}\_{t}\left(\theta\_{t}\right) $$ $$ \theta\_{t+1} = \theta\_{t} - \alpha\left[\left(1-v\right)\cdot\nabla\hat{L}\_{t}\left(\theta\_{t}\right) + v\cdot{g\_{t+1}}\right]$$ The authors suggest a rule of thumb of $v = 0.7$ and $\beta = 0.999$.

출처: Quasi-hyperbolic momentum and Adam for deep learning

소개 논문: Quasi-hyperbolic momentum and Adam for deep learning