In this paper, we study stochastic structured bandits for minimizing regret.

In this paper, we study stochastic structured bandits for minimizing regret.

The server aggregates these updates (typically by averaging) to construct a global model, and then sends the new model parameters to all clients.

Table 1: Results (mean onestandarddeviationover 10 replicates) onthemonotonicexamplein Section 5.1.2

To explain the decision of any regression and classification model, we extend the notion ofprobabilistic sufficient explanations (P-SE).