Adversarial Estimation of Riesz Representers

arXiv:2101.00009v3 Announce Type: replace-cross
Abstract: Many causal parameters are linear functionals of an underlying regression. The Riesz representer is a key component in the asymptotic variance of a semiparametrically estimated linear functional. We propose an adversarial framework to estimate the Riesz representer using general function spaces. We prove a nonasymptotic mean square rate in terms of an abstract quantity called the critical radius, then specialize it for neural networks, random forests, and reproducing kernel Hilbert spaces as leading cases. Our …

abstract adversarial arxiv causal cs.lg econ.em framework function functional general key linear mean parameters prove rate regression spaces square stat.ml terms type variance