Convergence of an online gradient method with inner-product penalty and adaptive momentum.

Hongmei Shao Dongpo Xu Gaofeng Zheng Lijun Liu

Published in: Neurocomputing (2012)

Keyphrases

gradient method
convergence rate
learning rate
convergence speed
log likelihood function
step size
recursive least squares
actor critic
negative matrix factorization
convex formulation
objective function
optimization methods
machine learning
multiresolution
optimization algorithm
policy gradient