Gaussian Process Bandits without Regret: An Experimental Design Approach

51 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules (2019, background): “These use methods such as manifold learning (Paschali et al., 2019), Bayesian Optimization (Tran et al., 2017), and generative adversarial networks which generate transformation sequences (Ratner et al., 2017).”
Human-in-the-Loop Interpretability Prior (2018, methodology): “Our overall approach will be to find a collection of models with high likelihood p(X|M) and then perform model-based optimization [27] to identify which priors p(M) to evaluate via user studies.”
Regret Bounds for Gaussian Process Bandit Problems (2010, unknown): “During the reviewing process of this work, another work (Srinivas et al., 2009) addressing regret bounds in GP optimization has appeared.”
Surrogating the surrogate: accelerating Gaussian-process-based global optimization with a mixture cross-entropy algorithm (2010, background): “Recent advances in this domain include the conditional entropy of the minimizer (Villemonteix et al., 2006) dealing with noisy evaluations and a multi-armed bandit criterion (Srinivas et al., 2009) to derive regret bounds.”
Combining active learning and reactive control for robot grasping (2010, methodology): “A similar merit function has previously been employed for multi-armed bandits in metric spaces, wherein GPR was used to share knowledge between discrete bandits [40].”