The following lemma is standard in the literature, see e.g.

How should a player who repeatedly plays a game against a no-regret learner strategize to maximize his utility?

In this section we discuss how to adapt existing linear bandit results (mostly in the regret setting) to sample complexity results.

For example, a recruiter (the decision maker) sequentially decides which job applicants to hire with the objective of minimizing errors (of hiring an unqualified applicant and rejecting aqualified one).

An example is the stochastic shortest path problem with random edge costs (e.g., traffic) and contextual features (e.g., lagged traffic, weather).

Reg. complexity of Algorithm 1: The main operations which depend on the number of datapointsnare lines 3, 418 and10.