Anticipated Regret and Product Innovation.
Baojun JiangChakravarthi NarasimhanÖzge TurutPublished in: Manag. Sci. (2017)
Keyphrases
- online learning
- lower bound
- confidence bounds
- expert advice
- loss function
- bandit problems
- minimax regret
- regret minimization
- online convex optimization
- upper confidence bound
- worst case
- genetic algorithm
- regret bounds
- multi armed bandit problems
- data sets
- reward function
- game theory
- upper bound
- active learning
- artificial neural networks
- data structure
- social networks