Randomized Quasi-Newton Updates Are Linearly Convergent Matrix Inversion Algorithms.

Robert M. Gower Peter Richtárik

Published in: SIAM J. Matrix Anal. Appl. (2017)

Keyphrases

quasi newton
matrix inversion
computational cost
learning algorithm
computational complexity
optimization methods
newton method
neural network
denoising
convergence rate
matrix factorization