Thompson Sampling with Diffusion Generative Prior
This work addresses the challenge of online decision-making across similar bandit tasks, offering a novel approach that could improve efficiency in scenarios with incomplete or noisy data.
The paper tackles the problem of meta-learning for bandit tasks by using a denoising diffusion model to learn priors from task distributions, combined with Thompson sampling to balance prior knowledge and noisy observations, achieving strong performance in experimental evaluations.
In this work, we initiate the idea of using denoising diffusion models to learn priors for online decision making problems. Our special focus is on the meta-learning for bandit framework, with the goal of learning a strategy that performs well across bandit tasks of a same class. To this end, we train a diffusion model that learns the underlying task distribution and combine Thompson sampling with the learned prior to deal with new tasks at test time. Our posterior sampling algorithm is designed to carefully balance between the learned prior and the noisy observations that come from the learner's interaction with the environment. To capture realistic bandit scenarios, we also propose a novel diffusion model training procedure that trains even from incomplete and/or noisy data, which could be of independent interest. Finally, our extensive experimental evaluations clearly demonstrate the potential of the proposed approach.