Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits.

Jongyeong Lee Junya Honda Chao-Kai Chiang Masashi Sugiyama

Published in: ICML (2023)

Keyphrases

multi objective
pareto optimality
multi armed bandit
random sampling
optimal solution
bayesian framework
sampling algorithm
monte carlo
sampling strategy
parameter space
neural network
multiobjective optimization
machine learning
prior knowledge
learning algorithm
sampling methods
prior model
genetic algorithm