Model-agnostic meta-learners for estimating heterogeneous treatment effects over time

Estimating heterogeneous treatment effects (HTEs) over time is crucial in many disciplines such as personalized medicine. Existing works for this task have mostly focused onmodel-basedlearners that adapt specific machine-learning models and adjustment mechanisms. In contrast, model-agnostic learners - so-calledmeta-learners- are largely unexplored. In our paper, we propose several meta-learners that are model-agnostic and thus can be used in combination with arbitrary machine learning models (e.g., transformers) to estimate HTEs over time. We then provide a comprehensive theoretical analysis that characterizes the different learners and that allows us to offer insights into when specific learners are preferable. Furthermore, we propose a novel IVW-DR-learner that (i) uses a doubly robust (DR) and orthogonal loss; and (ii) leverages inverse-variance weights (IVWs) that we derive to stabilize the DR-loss over time. Our IVWs downweight extreme trajectories due toproductsof inverse-propensities in the DR-loss, resulting in a lower estimation variance. Our IVW-DR-learner achieves superior performance in our experiments, particularly in regimes with low overlap and long time horizons.