Natasha 2: Faster Non-Convex Optimization Than SGD.

Zeyuan Allen-Zhu

Published in: NeurIPS (2018)

Keyphrases

convex optimization
interior point methods
low rank
primal dual
total variation
convex relaxation
semidefinite program
computer vision
norm minimization
stochastic gradient descent
high quality
image restoration
convex constraints
convex formulation
basis pursuit