Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization.

Hung Tran-The Sunil Gupta Santu Rana Svetha Venkatesh

Published in: AISTATS (2022)

Keyphrases

gaussian process
regret bounds
multi armed bandit
learning algorithm
semi supervised
prior knowledge
probability distribution
online learning
graph cuts
model selection
random sampling
hyperparameters
pairwise
theoretical guarantees
bregman divergences
bayesian networks
machine learning