Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm.
Junpei KomiyamaJunya HondaHiroshi NakagawaPublished in: CoRR (2016)
Keyphrases
- computationally efficient
- optimal solution
- worst case
- lower bound
- dynamic programming
- k means
- significant improvement
- np hard
- computational cost
- preprocessing
- theoretical analysis
- segmentation algorithm
- similarity measure
- cost function
- average case
- search space
- detection algorithm
- knapsack problem
- matching algorithm
- optimal cost
- exhaustive search
- loss function
- simulated annealing
- probabilistic model
- active learning