Login / Signup
Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling.
Shuaipeng Li
Penghao Zhao
Hailin Zhang
Xingwu Sun
Hao Wu
Dian Jiao
Weiyan Wang
Chengjun Liu
Zheng Fang
Jinbao Xue
Yangyu Tao
Bin Cui
Di Wang
Published in:
CoRR (2024)
Keyphrases
</>
learning rate
batch size
single item
convergence rate
learning algorithm
poisson process
batch mode
batch processing
convergence speed
optimal solution
dynamic programming
worst case
lot sizing
supervised learning
multistage
long run
fixed cost