Adam-mini: Use Fewer Learning Rates To Gain More.

Yushun Zhang Congliang Chen Ziniu Li Tian Ding Chenwei Wu Yinyu Ye Zhi-Quan Luo Ruoyu Sun

Published in: CoRR (2024)

Keyphrases

learning rate
learning algorithm
convergence rate
error function
covering numbers
gaussian kernels
uniform convergence
convergence speed
convergence theorem
weight vector
delta bar delta
distance measure
data mining
support vector