Results 121 to 130 of about 330,664 (214)

Universal subgradient and proximal bundle methods for convex and strongly convex hybrid composite optimization [PDF]

open access: yesarXiv
This paper develops two parameter-free methods for solving convex and strongly convex hybrid composite optimization problems, namely, a composite subgradient type method and a proximal bundle type method. Both functional and stationary complexity bounds for the two methods are established in terms of the unknown strong convexity parameter.
arxiv  

Home - About - Disclaimer - Privacy