Simultaneously achieving sublinear regret and constraint violations for online convex optimization with time-varying constraints.
Qingsong LiuWenfei WuLongbo HuangZhixuan FangPublished in: Perform. Evaluation (2021)
Keyphrases
- constraint violations
- online convex optimization
- online learning
- hard constraints
- long run
- soft constraints
- temporal constraints
- convex optimization
- multiple criteria
- newton method
- lower bound
- regret bounds
- cost function
- optimization problems
- constraint satisfaction
- np complete
- graphical models
- least squares
- multi objective