A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback.
Saeed MasoudianJulian ZimmertYevgeny SeldinPublished in: CoRR (2022)
Keyphrases
- single pass
- times faster
- optimization algorithm
- learning algorithm
- computational complexity
- k means
- linear programming
- data sets
- optimal solution
- estimation algorithm
- recognition algorithm
- similarity measure
- classification algorithm
- experimental study
- detection algorithm
- computational cost
- dynamic programming
- cost function
- objective function
- theoretical analysis
- segmentation method
- convex hull
- significant improvement
- artificial neural networks