Second-Order Step-Size Tuning of SGD for Non-Convex Optimization.

Camille Castera Jérôme Bolte Cédric Févotte Edouard Pauwels

Published in: Neural Process. Lett. (2022)

Keyphrases

convex optimization
step size
stochastic gradient descent
hessian matrix
convergence rate
cost function
convergence speed
interior point methods
total variation
higher order
primal dual
gradient method
wavelet coefficients
convex optimization problems
computer vision
least squares
interior point
multiscale