Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation

ArXi:2510.09908v3 Announce Type: replace-cross The rise of large-scale pretrained models has made it feasible to generate predictive or synthetic features at low cost, raising the question of how to incorporate such surrogate predictions into downstream decision-making. We study this problem in the setting of online linear contextual bandits, where contexts may be complex, nonstationary, and only partially observed.