Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions.

Nima Eshraghi Ben Liang

Published in: CoRR (2022)

Keyphrases

online convex optimization
online learning
convex optimization
long run
cost function
newton method
real time
efficient algorithms for solving
dynamic environments
online algorithms
least squares
convex hull
total variation
convergence analysis
regret bounds
search space reduction