astro-ph.SRMar 23, 2025

Generative Learner for Distributional Causal Effects

Authors: Maria Nareklishvili, Nicholas Polson, Vadim Sokolov

Organizations: Graduate School of Business, Stanford University · University of Glasgow, Adam Smith Business School · Booth School of Business, University of Chicago · Department of Systems Engineering and Operations Research, George Mason University

Abstract

We propose a generative learner for estimating conditional average treatment effects and characterizing the full distribution of these effects. The learner takes the form of a multi-head feed-forward neural network with three jointly estimated subnetworks: the propensity score, the conditional quantile function of the baseline outcome, and the conditional quantile treatment effect. Each quantile-indexed subnetwork combines a covariate representation with cosine quantile embeddings through element-wise multiplication. We then recover the conditional average treatment effect as an integral over conditional quantile treatment effects. Under the classical causal assumptions within the Neyman--Rubin potential outcomes framework, we find that the proposed generative learner reduces out-of-sample mean squared error relative to the generalized random forest, double machine learning, and generative adversarial networks, with gains ranging from 5.4% to 93.5% on average across experimental designs. In an empirical application, we formalize the Stefan--Boltzmann law within a unidirectional causal model and apply the method to publicly available stellar data. The estimated effects satisfy the restrictions the law implies.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates

    Feb 4, 2026Thatchanon Anancharoenkij, Donlapark PonnopratKernel Mean EmbeddingsConditional Distribution Estimation

  2. OrthoGen: A Generative Orthogonal Learner for Time-Varying Treatments

    Oct 7, 2026Tomàs Garriga, Valentyn Melnychuk, Konstantin Hess +4Causal Effect EstimationCausal Inference

  3. Distributional Causal Mediation via Conditional Generative Modeling

    May 3, 2026Jinlun Zhang, Haoneng Huang, Zishu Zhan +1Causal Effect EstimationCausal Mediation Analysis