Quantile-Regret Minimisation in Infinitely Many-Armed Bandits.
Arghya Roy ChaudhuriShivaram KalyanakrishnanPublished in: UAI (2018)
Keyphrases
- regret bounds
- multi armed bandit problems
- multi armed bandit
- multi armed bandits
- lower bound
- online learning
- bandit problems
- expert advice
- linear regression
- finite number
- regularized kernel
- central limit theorem
- loss function
- online convex optimization
- social networks
- confidence bounds
- neural network
- upper bound
- stochastic systems
- linear predictors
- weighted majority
- binary classification
- probabilistic model
- cooperative
- artificial intelligence