mlsanityData to 7 Oct 2026

Overlap-weighted orthogonal meta-learner for treatment effect estimation over time

arXiv 2510.19643 ↗First posted 22 Oct 2025cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Estimating heterogeneous treatment effects (HTEs) in time-varying settings is particularly challenging, as the probability of observing certain treatment sequences decreases exponentially with longer prediction horizons. Thus, the observed data contain little support for many plausible treatment sequences, which creates severe overlap problems. Existing meta-learners for the time-varying setting typically assume adequate treatment overlap, and thus suffer from exploding estimation variance when the overlap is low. To address this problem, we introduce a novel overlap-weighted orthogonal (WO) meta-learner for estimating HTEs that targets regions in the observed data with high probability of receiving the interventional treatment sequences. This offers a fully data-driven approach through which our WO-learner can counteract instabilities as in existing meta-learners and thus obtain more reliable HTE estimates. Methodologically, we develop a novel Neyman-orthogonal population risk function that minimizes the overlap-weighted oracle risk. We show that our WO-learner has the favorable property of Neyman-orthogonality, meaning that it is robust against misspecification in the nuisance functions. Further, our WO-learner is fully model-agnostic and can be applied to any machine learning model. Through extensive experiments with both transformer and LSTM backbones, we demonstrate the benefits of our novel WO-learner.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 49 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

25 of 49 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 475
  3. 2017Quasi-Oracle Estimation of Heterogeneous Treatment Effectscited by 328
  4. 2020Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representationscited by 154
  5. 2021Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithmscited by 144
  6. 2022Semiparametric doubly robust targeted double machine learning: a reviewcited by 129
  7. 2019MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-IIIcited by 121
  8. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
  9. 2024Causal machine learning for predicting treatment outcomescited by 73
  10. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
  11. 2020Identifying Causal-Effect Inference Failure with Uncertainty-Aware Modelscited by 57
  12. 2024Applied Causal Inference Powered by ML and AIcited by 30
13 more
  1. 2022Estimating average causal effects from patient trajectoriescited by 29
  2. 2020Double/Debiased Machine Learning for Dynamic Treatment Effects via g-Estimationcited by 27
  3. 2023Bayesian Neural Controlled Differential Equations for Treatment Effect Estimationcited by 26
  4. 2020Counterfactual Predictions under Runtime Confoundingcited by 22
  5. 2024Model-agnostic meta-learners for estimating heterogeneous treatment effects over timecited by 18
  6. 2024Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformercited by 10
  7. 2024Simplifying debiased inference via automatic differentiation and probabilistic programmingcited by 10
  8. 2024IGC-Net for conditional average potential outcome estimation over timecited by 10
  9. 2025Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Datacited by 10
  10. 2024Stabilized Neural Prediction of Potential Outcomes in Continuous Timecited by 7
  11. 2025Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoptioncited by 6
  12. 2023The Connection Between R-Learning and Inverse-Variance Weighting for Estimation of Heterogeneous Treatment Effectscited by 3
  13. 2025Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Debiased neural operators for estimating functionalscited by 1
  2. 2026Targeted Synthetic Control Methodcited by 0
  3. 2026Orthogonal Learner for Estimating Heterogeneous Long-Term Treatment Effectscited by 0