mlsanityData to 14 Oct 2026

B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding

arXiv 2304.10577 ↗First posted 20 Apr 2023cs.LG stat.MLcited by 28

Not on the map. Why?

Abstract (arXiv)

Estimating heterogeneous treatment effects from observational data is a crucial task across many fields, helping policy and decision-makers take better actions. There has been recent progress on robust and efficient methods for estimating the conditional average treatment effect (CATE) function, but these methods often do not take into account the risk of hidden confounding, which could arbitrarily and unknowingly bias any causal estimate based on observational data. We propose a meta-learner called the B-Learner, which can efficiently learn sharp bounds on the CATE function under limits on the level of hidden confounding. We derive the B-Learner by adapting recent results for sharp and valid bounds of the average treatment effect (Dorn et al., 2021) into the framework given by Kallus & Oprescu (2023) for robust and model-agnostic learning of conditional distributional treatment effects. The B-Learner can use any function estimator such as random forests and deep neural networks, and we prove its estimates are valid, sharp, efficient, and have a quasi-oracle property with respect to the constituent estimators under more general conditions than existing methods. Semi-synthetic experimental comparisons validate the theoretical findings, and we use real-world data to demonstrate how the method might be used in practice.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 14 of its 37 references that are in the map. First posted on arXiv 20 Apr 2023.

Builds on

14 of 37 references.

References · 14

  1. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
  2. 2017Quasi-Oracle Estimation of Heterogeneous Treatment Effectscited by 332
  3. 2016Generalized Random Forestscited by 312
  4. 2019Orthogonal Statistical Learningcited by 151
  5. 2018Interval Estimation of Individual-Level Causal Effects Under Unobserved Confoundingcited by 51
  6. 2021Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confoundingcited by 50
  7. 2021Conformal Sensitivity Analysis for Individual Treatment Effectscited by 40
  8. 2018Bounds on the conditional and average treatment effect with unobserved confounding factorscited by 39
  9. 2021Sharp Sensitivity Analysis for Inverse Propensity Weighting via Quantile Balancingcited by 32
  10. 2021Doubly-Valid/Doubly-Sharp Sensitivity Analysis for Causal Inference with Unmeasured Confoundingcited by 28
  11. 2021Long Story Short: Omitted Variable Bias in Causal Machine Learningcited by 23
  12. 2022Robust and Agnostic Learning of Conditional Distributional Treatment Effectscited by 18
2 more
  1. 2022Treatment Effect Risk: Bounds and Inferencecited by 12
  2. 2021Causal effect on a target population: a sensitivity analysis to handle missing covariatescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 9; 2025: 6; 2026: 5.

28 papers.

Sort:

By area:

  1. 2024Causal machine learning for predicting treatment outcomescited by 74
  2. 2023Bayesian Neural Controlled Differential Equations for Treatment Effect Estimationcited by 26
  3. 2023Sharp Bounds for Generalized Causal Sensitivity Analysiscited by 24
  4. 2023Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimationcited by 20
  5. 2023A Neural Framework for Generalized Causal Sensitivity Analysiscited by 17
  6. 2023Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Modelcited by 14
  7. 2024Meta-Learners for Partially-Identified Treatment Effects Across Multiple Environmentscited by 11
  8. 2023Causal Fairness under Unobserved Confounding: A Neural Sensitivity Frameworkcited by 10
  9. 2024IGC-Net for conditional average potential outcome estimation over timecited by 10
  10. 2024Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learnercited by 10
  11. 2025Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Datacited by 10
  12. 2023Hidden yet quantifiable: A lower bound for confounding strength using randomized trialscited by 8
16 more
  1. 2023Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confoundingcited by 7
  2. 2024Constructing Confidence Intervals for Average Treatment Effects from Multiple Datasetscited by 6
  3. 2025Efficient and Sharp Off-Policy Learning under Unobserved Confoundingcited by 6
  4. 2025Differentially Private Learners for Heterogeneous Treatment Effectscited by 5
  5. 2024Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processescited by 3
  6. 2024Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysiscited by 3
  7. 2025Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inferencecited by 3
  8. 2026Amortizing Causal Sensitivity Analysis via Prior Data-Fitted Networkscited by 3
  9. 2024Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Datacited by 2
  10. 2026Information-Theoretic Causal Bounds under Unmeasured Confoundingcited by 2
  11. 2025Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoringcited by 1
  12. 2026Causal Inference on Networks under Misspecified Exposure Mappings: A Partial Identification Frameworkcited by 1
  13. 2024Neural Networks with Causal Graph Constraints: A New Approach for Treatment Effects Estimationcited by 0
  14. 2025Conditional Average Treatment Effect Estimation Under Hidden Confounderscited by 0
  15. 2026Treatment Effect Estimation with Differentiated Networked Effect on Graph Datacited by 0
  16. 2026What You Observe Determines How You Identify Causal Effects: Evaluating Causal Models across Observational Viewscited by 0