Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm.
Junpei KomiyamaJunya HondaHiroshi NakagawaPublished in: ICML (2016)
Keyphrases
- computationally efficient
- lower bound
- cost function
- np hard
- worst case
- optimal solution
- detection algorithm
- optimization algorithm
- objective function
- computational complexity
- dynamic programming
- preprocessing
- learning algorithm
- matching algorithm
- average case
- upper bound
- computational cost
- expectation maximization
- simulated annealing
- segmentation algorithm
- special case
- random sampling
- search space