We study the problem of best-arm identification with fixed confidence in stochastic linear
bandits. The objective is to identify the best arm with a given level of certainty while …

We study the problem of active pure exploration with fixed confidence in generic stochastic
bandit environments. The goal of the learner is to answer a query about the environment …

In recent years methods from optimal linear experimental design have been leveraged to
obtain state of the art results for linear bandits. A design returned from an objective such as …

In the stochastic contextual bandit setting, regret-minimizing algorithms have been
extensively researched, but their instance-minimizing best-arm identification counterparts …

We explore a new model of bandit experiments where a potentially nonstationary sequence
of contexts influences arms' performance. Context-unaware algorithms risk confounding …

We consider the development of adaptive, instance-dependent algorithms for interactive
decision making (bandits, reinforcement learning, and beyond) that, rather than only …

In the contextual linear bandit setting, algorithms built on the optimism principle fail to exploit
the structure of the problem and have been shown to be asymptotically suboptimal. In this …

A long line of works characterizes the sample complexity of regret minimization in sequential
decision-making by min-max programs. In the corresponding saddle-point game, the min …

We study the problem of experiment planning with function approximation in contextual
bandit problems. In settings where there is a significant overhead to deploying adaptive …

The linear contextual bandit literature is mostly focused on the design of efficient learning
algorithms for a given representation. However, a contextual bandit problem may admit …