Best-of-three-worlds Analysis for Linear Bandits with Follow-the-regularized-leader Algorithm.
Fang KongCanzhe ZhaoShuai LiPublished in: CoRR (2023)
Keyphrases
- experimental evaluation
- preprocessing
- learning algorithm
- computational cost
- detection algorithm
- worst case
- np hard
- linear complexity
- improved algorithm
- times faster
- computational complexity
- matching algorithm
- tree structure
- expectation maximization
- recognition algorithm
- closed form
- regularized least squares
- segmentation algorithm
- input data
- cost function
- k means
- optimization algorithm
- theoretical analysis
- linear programming
- simulated annealing
- piecewise linear
- optimal solution