Representation Learning for Sample-Efficient CATE Estimation by Leveraging Multiple Outcomes
Theoretically, it is proved that when the auxiliary outcomes satisfy a set of surrogacy conditions and the representation retains relevant covariate information, the original CATE is identified when the high-dimensional covariates are replaced by the learned representation.
Maitreyi Swaroop, Shikha Bhat, Samantha Rodriguez et al.
· 0 citations