Stochastic linear bandits with high-dimensional sparse features are a practical model for a
variety of domains, such as personalized medicine and online advertising. We derive a …

Consider the sequential optimization of a continuous, possibly non-convex, and expensive
to evaluate objective function $ f $. The problem can be cast as a Gaussian Process (GP) …

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

In the stochastic linear contextual bandit setting there exist several minimax procedures for
exploration with policies that are reactive to the data being acquired. In practice, there can …

In situ magnetic field measurements are often difficult to obtain due to the presence of stray
magnetic fields generated by spacecraft electrical subsystems. The conventional solution is …

The use of magnetometers for space exploration is inhibited by magnetic noise generated
by spacecraft electrical systems. Mechanical booms are traditionally used to extend …

Spacecraft magnetic field measurements are frequently degraded by stray magnetic fields
originating from onboard electrical systems. These interference signals can mask the natural …

We study the best-arm identification problem with fixed confidence when contextual
(covariate) information is available in stochastic bandits. Although we can use contextual …

We study the best policy identification problem for contextual bandits through the lens of
Bayesian optimal experimental design. Motivated by practical constraints when deploying …

Offline reinforcement learning is used to train policies in scenarios where real-time access to
the environment is expensive or impossible. As a natural consequence of these harsh …