Regret bounded by gradual variation for online convex optimization.

Tianbao Yang Mehrdad Mahdavi Rong Jin Shenghuo Zhu

Published in: Mach. Learn. (2014)

Keyphrases

online convex optimization
online learning
long run
convex optimization
newton method
cost function
regret bounds
efficient algorithms for solving
feature selection
sufficient conditions
optimal policy
convergence analysis