Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards

In this work, we study the performance of the Thompson Sampling algorithm for Contextual Bandit problems based on the framework introduced by [1] and their concept of lifted information ratio. First, we prove a comprehensive bound on the Thompson Sampling expected cumulative regret that depends on the mutual information of the environment parameters and the history. Then, we introduce new bounds on the lifted information ratio that hold for sub-Gaussian rewards, thus generalizing the results from [1] which analysis requires binary rewards. Finally, we provide explicit regret bounds for the special cases of unstructured bounded contextual bandits, structured bounded contextual bandits with Laplace likelihood, structured Bernoulli bandits, and bounded linear contextual bandits.