We consider the problem of identifying the best arm in stochastic Multi-Armed Bandits
(MABs) using a fixed sampling budget. Characterizing the minimal instance-specific error …

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

In fixed budget bandit identification, an algorithm sequentially observes samples from
several distributions up to a given final time. It then answers a query about the set of …

A Top Two sampling rule for bandit identification is a method which selects the next arm to
sample from among two candidate arms, a leader and a challenger. Due to their simplicity …

We study the problem of best-arm identification with fixed budget in stochastic two-arm
bandits with Bernoulli rewards. We prove that surprisingly, there is no algorithm that (i) …

Static supervised learning—in which experimental data serves as a training sample for the
estimation of an optimal treatment assignment policy—is a commonly assumed framework of …

We address the problem of best arm identification (BAI) with a fixed budget for two-armed
Gaussian bandits. In BAI, given multiple arms, we aim to find the best arm, an arm with the …

Practitioners conducting adaptive experiments often encounter two competing priorities:
reducing the cost of experimentation by effectively assigning treatments during the …

Economic policies often involve dynamic interventions, where individuals receive repeated
interventions over multiple periods. This dynamics makes past responses informative to …

We study the best-arm identification (BAI) problem with a fixed budget and contextual
(covariate) information. In each round of an adaptive experiment, after observing contextual …