Consider a recommendation platform that interacts with a finite set of users in an online fashion. Users arrive at the platform and receive a recommendation.

Distributional shifts pose a significant challenge to achieving robustness in contemporary machine learning.

We consider the problem of designing contextual bandit algorithms in the "cross-learning" setting of Balseiro et al., where the learner observes the loss for the action

We consider the problem of designing contextual bandit algorithms in the "cross-learning" setting of Balseiro et al., where the learner observes the loss for the action

Neural Information Processing Systems http://nips.cc/