Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate.

Miao Lu Beining Wu Xiaodong Yang Difan Zou

Published in: ICLR (2024)

Keyphrases

learning rate
stochastic gradient descent
weight vector
step size
convergence rate
convergence speed
learning algorithm
matrix factorization
least squares
training speed
loss function
random forests
support vector machine
online algorithms
multiple kernel learning
perceptron algorithm
data mining