VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments
This addresses a key challenge in causal inference for continuous treatments, offering a method that enhances model expressiveness and robustness, though it is incremental in advancing neural network-based approaches.
The paper tackled the problem of estimating average dose-response curves (ADRFs) from observational data with continuous treatments, proposing VCNet and functional targeted regularization to achieve continuous and doubly robust ADRF estimates with improved finite sample performance.
Motivated by the rising abundance of observational data with continuous treatments, we investigate the problem of estimating the average dose-response curve (ADRF). Available parametric methods are limited in their model space, and previous attempts in leveraging neural network to enhance model expressiveness relied on partitioning continuous treatment into blocks and using separate heads for each block; this however produces in practice discontinuous ADRFs. Therefore, the question of how to adapt the structure and training of neural network to estimate ADRFs remains open. This paper makes two important contributions. First, we propose a novel varying coefficient neural network (VCNet) that improves model expressiveness while preserving continuity of the estimated ADRF. Second, to improve finite sample performance, we generalize targeted regularization to obtain a doubly robust estimator of the whole ADRF curve.