Such feedback can be stochastic, e.g. the

For example, in the Pandemic Response Challenge experiment, the context consisted of data about the geographic region for which the predictions were made, e.g., historical data of COVID-19 cases and intervention policies; actions were future schedules of intervention policies for the region; and outcomes were predicted future cases of COVID-19 along with the stringency

Its simplicity also raises many practical and theoretical questions about the task-relations it can exploit and the settings in which it can succeed.

's convergence rate is state-of-the-art: achieving quadratic speedup for strongly convex and sublinear speedup of order 2/3 for smooth non-convex objectives.

In this work, we investigate the problem of federated hyperparameter tuning.

In this work, we investigate the problem of federated hyperparameter tuning.

(Section 3).