Login / Signup
MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients.
Chen Zhu
Yu Cheng
Zhe Gan
Furong Huang
Jingjing Liu
Tom Goldstein
Published in:
ECML/PKDD (3) (2021)
Keyphrases
</>
step size
cost function
convergence rate
convergence speed
evolutionary programming
faster convergence
evolutionary algorithm
wavelet coefficients