Linear contextual bandits represent a fundamental class of models with numerous real-world applications, and it is critical to developing algorithms that can effectively manage noise with unknown variance, ensuring provable guarantees for both worst-case constant-variance noise and deterministic reward scenarios.

However, the availability of such resources remains scarce and evaluation faces added complexity due to reproducibility issues in experimental protocols.

GNNs to mitigate the bias as well as boost their utility in an end-to-end manner.

The optimization phase in deep learning consists in minimizing an objective function w.r.t. the set of

In the first case, points arrive sequentially, and only a summary can be stored in memory.