On the Noisy Gradient Descent that Generalizes as SGD.

Jingfeng Wu Wenqing Hu Haoyi Xiong Jun Huan Vladimir Braverman Zhanxing Zhu

Published in: ICML (2020)

Keyphrases

stochastic gradient descent
cost function
loss function
noisy environments
least squares
alternating least squares
incomplete data
missing data
particle swarm optimization
objective function
training data
data sets
matrix factorization
step size
random forests
conjugate gradient
website