Sampling depth trade-off in function estimation under a two-level design

Many modern statistical applications involve a two-level sampling scheme that first samples subjects from a population and then samples observations on each subject. These schemes often are designed to learn both the population-level functional structures shared by the subjects and the functional characteristics specific to individual subjects. Common wisdom suggests that learning population-level structures benefits from sampling more subjects whereas learning subject-specific structures benefits from deeper sampling within each subject. Oftentimes these two objectives compete for limited sampling resources, which raises the question of how to optimally sample at the two levels. We quantify such sampling-depth trade-offs by establishing the $L_2$ minimax risk rates for learning the population-level and subject-specific structures under a hierarchical Gaussian process model framework where we consider a Bayesian and a frequentist perspective on the unknown population-level structure. These rates provide general lessons for designing two-level sampling schemes. Interestingly, subject-specific learning occasionally benefits more by sampling more subjects than by deeper within-subject sampling. We also construct estimators that adapt to unknown smoothness and achieve the corresponding minimax rates. We conduct two simulation experiments validating our theory and illustrating the sampling trade-off in practice, and apply these estimators to two real datasets.