mlsanityData to 7 Oct 2026

GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes

arXiv 2509.22953 ↗First posted 26 Sep 2025cs.LG stat.MLcited by 1

Not on the map. Why?

Abstract (arXiv)

Various deep generative models have been proposed to estimate potential outcomes distributions from observational data. However, none of them have the favorable theoretical property of general Neyman-orthogonality and, associated with it, quasi-oracle efficiency and double robustness. In this paper, we introduce a general suite of generative Neyman-orthogonal (doubly-robust) learners that estimate the conditional distributions of potential outcomes. Our proposed generative doubly-robust learners (GDR-learners) are flexible and can be instantiated with many state-of-the-art deep generative models. In particular, we develop GDR-learners based on (a) conditional normalizing flows (which we call GDR-CNFs), (b) conditional generative adversarial networks (GDR-CGANs), (c) conditional variational autoencoders (GDR-CVAEs), and (d) conditional diffusion models (GDR-CDMs). Unlike the existing methods, our GDR-learners possess the properties of quasi-oracle efficiency and rate double robustness, and are thus asymptotically optimal. In a series of (semi-)synthetic experiments, we demonstrate that our GDR-learners are very effective and outperform the existing methods in estimating the conditional distributions of potential outcomes.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 62 of its 100 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

62 of 100 references.

References · 62

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  4. 2015Variational Inference with Normalizing Flowscited by 2,161
  5. 2016HyperNetworkscited by 1,003
  6. 2019An Introduction to Variational Autoencoderscited by 997
  7. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  8. 2019Neural Spline Flowscited by 590
  9. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 475
  10. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  11. 2017Quasi-Oracle Estimation of Heterogeneous Treatment Effectscited by 328
  12. 2016Learning Representations for Counterfactual Inferencecited by 327
38 more
  1. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  2. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  3. 2018Neural Autoregressive Flowscited by 207
  4. 2017Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processescited by 156
  5. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  6. 2019Orthogonal Statistical Learningcited by 150
  7. 2021Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithmscited by 144
  8. 2022Semiparametric doubly robust targeted double machine learning: a reviewcited by 129
  9. 2021Counterfactual Generative Networkscited by 111
  10. 2017Automated versus do-it-yourself methods for causal inference: Lessons learned from a data analysis competitioncited by 106
  11. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  12. 2024Causal machine learning for predicting treatment outcomescited by 73
  13. 2020Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effectscited by 72
  14. 2020Treatment effect estimation with disentangled latent factorscited by 63
  15. 2018Conditional Density Estimation with Bayesian Normalising Flowscited by 54
  16. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  17. 2021Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confoundingcited by 50
  18. 2020Counterfactual Representation Learning with Balancing Weightscited by 45
  19. 2021Semiparametric counterfactual density estimationcited by 42
  20. 2021Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regressioncited by 40
  21. 2022Causal Effect Identification in Cluster DAGscited by 33
  22. 2023Bayesian Neural Controlled Differential Equations for Treatment Effect Estimationcited by 26
  23. 2019Noise Regularization for Conditional Density Estimationcited by 23
  24. 2022Normalizing Flows for Interventional Density Estimationcited by 21
  25. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 21
  26. 2024Neural Causal Abstractionscited by 20
  27. 2022Robust and Agnostic Learning of Conditional Distributional Treatment Effectscited by 18
  28. 2024Model-agnostic meta-learners for estimating heterogeneous treatment effects over timecited by 18
  29. 2023Counterfactual Generative Models for Time-Varying Treatmentscited by 17
  30. 2024DiffPO: A causal diffusion model for learning distributions of potential outcomescited by 17
  31. 2018Causal effects based on distributional distancescited by 15
  32. 2022CVAE-H: Conditionalizing Variational Autoencoders via Hypernetworks and Trajectory Forecasting for Autonomous Drivingcited by 13
  33. 2023The Fundamental Limits of Structure-Agnostic Functional Estimationcited by 12
  34. 2023One-Step Estimation of Differentiable Hilbert-Valued Parameterscited by 11
  35. 2023An Efficient Doubly-Robust Test for the Kernel Treatment Effectcited by 10
  36. 2022OCD: Learning to Overfit with Conditional Diffusion Modelscited by 9
  37. 2021Estimating Potential Outcome Distributions with Collaborating Causal Networkscited by 8
  38. 2022Feature Selection for Discovering Distributional Treatment Effect Modifierscited by 7

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ORTHOBO: Orthogonal Bayesian Hyperparameter Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026OrthoGen: A Generative Orthogonal Learner for Time-Varying Treatments
  2. 2024Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding
  3. 2022Benign Autoencoders
  4. 2025Manifold Decoders: A Framework for Generative Modeling from Nonlinear Embeddings
  5. 2022Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
  6. 2025UNO: Unlearning via Orthogonalization in Generative models
  7. 2024On Divergence Measures for Training GFlowNets
  8. 2026PAPT++: Risk-Aware Adversarial Tuning and Generation for Single Domain Generalization