Dynamic Regret of Online Mirror Descent for Relatively Smooth Convex Cost Functions.
Nima EshraghiBen LiangPublished in: IEEE Control. Syst. Lett. (2022)
Keyphrases
- online convex optimization
- online learning
- long run
- convex optimization
- cost function
- newton method
- dynamic environments
- field of view
- online algorithms
- efficient algorithms for solving
- real time
- objective function
- linear programming
- convex hull
- piecewise linear
- piecewise constant
- global convergence
- search space reduction
- data sets