Adaptive experimental designs can dramatically improve efficiency in randomized trials. But
with adaptively collected data, common estimators based on sample means and inverse …

It has become increasingly common for data to be collected adaptively, for example using
contextual bandits. Historical data of this type can be used to evaluate other treatment …

Abstract Response-Adaptive Randomization (RAR) is part of a wider class of data-
dependent sampling algorithms, for which clinical trials are typically used as a motivating …

One of the key drivers of complexity in the classical (stochastic) multi-armed bandit (MAB)
problem is the difference between mean rewards in the top two arms, also known as the …

Data bias is a major concern in biomedical research, especially when evaluating large-scale
observational datasets. It leads to imprecise predictions and inconsistent estimates in …

In bandit multiple hypothesis testing, each arm corresponds to a different null hypothesis that
we wish to test, and the goal is to design adaptive algorithms that correctly identify large set …

We demonstrate that a wide array of machine learning algorithms are specific instances of
one single paradigm: reciprocal learning. These instances range from active learning over …

Entropy regularization is known to improve exploration in sequential decision-making
problems. We show that this same mechanism can also lead to nearly unbiased and lower …

In bandit algorithms, the randomly time-varying adaptive experimental design makes it
difficult to apply traditional limit theorems to off-policy evaluation of the treatment effect …

Applications of reinforcement learning (RL) for supporting, managing and improving
decision-making are becoming increasingly popular in a variety of medicine and healthcare …