O. P. Ferreira, M. S. Louzeiro, L. F. Prudente
Published 2018-08-20Version 1
The subgradient method for convex optimization problems on complete Riemannian manifolds with lower bounded sectional curvature is analyzed in this paper. Iteration-complexity bounds of the subgradient method with exogenous step-size and Polyak's step-size are stablished, completing and improving recent results on the subject.
Horoballs and the subgradient method
A subgradient method with constant step-size for $\ell_1$-composite optimization
Subgradient methods near active manifolds: saddle point avoidance, local convergence, and asymptotic normality
![QR code for arXiv:1808.06274 [math.OC]](http://oss.arxitics.com/images/favicon.svg)