Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates.

Zhuanghua Liu Luo Luo Bryan Kian Hsiang Low

Published in: AAAI (2024)

Keyphrases

convergence rate
low memory requirements
step size
learning rate

convergence speed
global convergence
primal dual
mutation operator

faster convergence
numerical stability
stopping criterion
gaussian kernels

neural network
high dimensional
artificial neural networks
conjugate gradient