An incremental quasi-Newton method with a local superlinear convergence rate.

Aryan Mokhtari Mark Eisen Alejandro Ribeiro

Published in: ICASSP (2017)

Keyphrases

convergence rate
quasi newton method
step size
quasi newton
convergence speed
learning rate
limited memory
objective function
global convergence
gradient method
primal dual
numerical stability
multi objective
faster convergence rate
neural network
convergence analysis
memory space
least squares
decision making