Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization.
Jonathan ScarlettIlija BogunovicVolkan CevherPublished in: CoRR (2017)
Keyphrases
- gaussian process
- lower bound
- regret bounds
- gaussian processes
- upper bound
- gaussian process regression
- bayesian framework
- approximate inference
- regression model
- gaussian process classification
- latent variables
- hyperparameters
- semi supervised
- model selection
- np hard
- objective function
- worst case
- expectation propagation
- random sampling
- online learning
- bandit problems
- optimal solution
- covariance function
- sparse approximations
- cross validation
- gaussian process models
- multi armed bandit
- incomplete data
- bayesian inference
- support vector
- similarity measure