STL-SGD: Speeding Up Local SGD with Stagewise Communication Period.

Shuheng Shen Yifei Cheng Jingchang Liu Linli Xu

Published in: AAAI (2021)

Keyphrases

stochastic gradient descent
loss function
communication networks
least squares
data sets
communication overhead
neural network
pairwise
multi class
matrix factorization
information exchange
communication channels