Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits.
Huasen WuR. SrikantXin LiuChong JiangPublished in: CoRR (2015)
Keyphrases
- worst case
- regret bounds
- learning algorithm
- recently developed
- lower bound
- orders of magnitude
- times faster
- data structure
- computational complexity
- upper confidence bound
- machine learning
- regret minimization
- multi armed bandit
- online algorithms
- computational efficiency
- machine learning algorithms
- theoretical analysis
- computationally efficient
- online learning
- significant improvement
- decision trees