We study a constructive algorithm that approximates Gateaux derivatives for statistical functionals by finite-differencing, with a focus on causal inference functionals. We consider the case where probability distributions are not known a priori but also need to be estimated from data. These estimated distributions lead to empirical Gateaux derivatives, and we study the relationships between empirical, numerical, and analytical Gateaux derivatives. Starting with a case study of counterfactual mean estimation, we instantiate the exact relationship between finite-differences and the analytical Gateaux derivative. We then derive requirements on the rates of numerical approximation in perturbation and smoothing that preserve the statistical benefits of one-step adjustments, such as rate-double-robustness. We then study more complicated functionals such as dynamic treatment regimes and the linear-programming formulation for policy optimization in infinite-horizon Markov decision processes. The newfound ability to approximate bias adjustments in the presence of arbitrary constraints illustrates the usefulness of constructive approaches for Gateaux derivatives. We also find that the statistical structure of the functional (rate-double robustness) can permit less conservative rates of finite-difference approximation. This property, however, can be specific to particular functionals, e.g. it occurs for the counterfactual mean but not the infinite-horizon MDP policy value.
翻译:我们研究一种建设性的算法,通过有限的差异来接近统计功能的Gateaux衍生物,重点是因果推断功能。我们考虑了概率分布并不先验,但需要从数据中估计。这些估计分布导致经验性的Gateaux衍生物,我们研究经验性、数字性和分析性Gateaux衍生物之间的关系。从反事实平均估计的案例研究开始,我们即时计算有限差异与分析型Gateaux衍生物之间的确切关系。我们随后提出有关数字接近率的要求,以扰动和平滑率保持一步调整的统计效益,如汇率双色暴动等。我们然后研究更复杂的功能,如动态治疗制度和在Flot-Horizon Markov决策过程中政策优化的线性方案制定。从对任意制约存在偏差调整的最近发现的能力,说明对Gateaux衍生物采取建设性办法的效用。我们发现,功能(双倍坚固度)的统计结构可以允许低保守度调整率,但不会允许固定-软度政策的具体值。这一功能-正正值是特定。