Escape saddle points faster on manifolds via perturbed Riemannian stochastic recursive gradient.

Andi Han Junbin Gao

Published in: CoRR (2020)

Keyphrases

saddle points
manifold learning
scale space
lie group
riemannian manifolds
critical points
euclidean space
saddle point
tangent space
low dimensional
shape analysis
endpoints
vector field
high dimensional
genetic algorithm
euclidean distance
multiscale