Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond.
Dheeraj BabyYu-Xiang WangPublished in: CoRR (2022)
Keyphrases
- online learning
- regret bounds
- online convex optimization
- distance education
- online course
- dynamic programming
- globally optimal
- higher education
- computer mediated
- blended learning
- semi infinite programming
- distance learning
- e learning
- lower bound
- worst case
- asymptotically optimal
- online algorithms
- active learning
- expert advice
- multi armed bandit
- dynamic environments
- least squares