Regret Bounds for Safe Gaussian Process Bandit Optimization.
Sanae AmaniMahnoosh AlizadehChristos ThrampoulidisPublished in: ISIT (2021)
Keyphrases
- gaussian process
- regret bounds
- multi armed bandit
- regression model
- approximate inference
- online learning
- linear regression
- bayesian framework
- semi supervised
- hyperparameters
- latent variables
- lower bound
- model selection
- cross validation
- upper bound
- pairwise
- closed form
- machine learning
- prior knowledge
- feature selection