Quasi-potential as an implicit regularizer for the loss function in the stochastic gradient descent.

Wenqing Hu Zhanxing Zhu Haoyi Xiong Jun Huan

Published in: CoRR (2019)

Keyphrases

loss function
stochastic gradient descent
pairwise
support vector
logistic regression
matrix factorization
step size
least squares
learning models
boosting algorithms
semi supervised
weight vector
learning algorithm
total variation
importance sampling