mlsanityData to 7 Oct 2026

Orthogonal Statistical Learning

arXiv 1901.09036 ↗First posted 25 Jan 2019math.ST cs.LG econ.EMcited by 150

Not on the map. Why?

Abstract (arXiv)

We provide non-asymptotic excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target parameter depends on an unknown nuisance parameter that must be estimated from data. We analyze a two-stage sample splitting meta-algorithm that takes as input arbitrary estimation algorithms for the target parameter and nuisance parameter. We show that if the population risk satisfies a condition called Neyman orthogonality, the impact of the nuisance estimation error on the excess risk bound achieved by the meta-algorithm is of second order. Our theorem is agnostic to the particular algorithms used for the target and nuisance and only makes an assumption on their individual performance. This enables the use of a plethora of existing results from machine learning to give new guarantees for learning with a nuisance component. Moreover, by focusing on excess risk rather than parameter estimation, we can provide rates under weaker assumptions than in previous works and accommodate settings in which the target parameter belongs to a complex nonparametric class. We provide conditions on the metric entropy of the nuisance and target classes such that oracle rates of the same order as if we knew the nuisance parameter are achieved.

Key facts. Cited by 150 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 25; 2023: 25; 2024: 28; 2025: 27; 2026: 29.

150 papers.

Sort:

By area:

  1. 2022A Review of Off-Policy Evaluation in Reinforcement Learningcited by 92
  2. 2021On Inductive Biases for Heterogeneous Treatment Effect Estimationcited by 74
  3. 2024Causal machine learning for predicting treatment outcomescited by 73
  4. 2021Causally motivated Shortcut Removal Using Auxiliary Labelscited by 55
  5. 2021Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiencycited by 54
  6. 2021Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approachcited by 43
  7. 2025CausalPFN: Amortized Causal Effect Estimation via In-Context Learningcited by 43
  8. 2022Doubly Robust Distributionally Robust Off-Policy Evaluation and Learningcited by 34
  9. 2024Applied Causal Inference Powered by ML and AIcited by 30
  10. 2025Foundation Models for Causal Inference via Prior-Data Fitted Networkscited by 30
  11. 2021Knowledge Distillation as Semiparametric Inferencecited by 29
  12. 2022Estimating average causal effects from patient trajectoriescited by 29
38 more
  1. 2021Doubly-Valid/Doubly-Sharp Sensitivity Analysis for Causal Inference with Unmeasured Confoundingcited by 28
  2. 2023B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confoundingcited by 28
  3. 2022Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processescited by 26
  4. 2022Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimationcited by 25
  5. 2022Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimationcited by 25
  6. 2021Minimax Kernel Machine Learning for a Class of Doubly Robust Functionals with Application to Proximal Causal Inferencecited by 20
  7. 2022Future-Dependent Value-Based Off-Policy Evaluation in POMDPscited by 20
  8. 2022Robust and Agnostic Learning of Conditional Distributional Treatment Effectscited by 18
  9. 2022Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Modelscited by 18
  10. 2023Doubly Robust Self-Trainingcited by 18
  11. 2024Model-agnostic meta-learners for estimating heterogeneous treatment effects over timecited by 18
  12. 2024DiffPO: A causal diffusion model for learning distributions of potential outcomescited by 17
  13. 2023Causal isotonic calibration for heterogeneous treatment effectscited by 16
  14. 2023Reliable Off-Policy Learning for Dosage Combinationscited by 15
  15. 2022Differentially Private Estimation of Heterogeneous Causal Effectscited by 14
  16. 2022Inference on Strongly Identified Functionals of Weakly Identified Functionscited by 12
  17. 2022Learning from a Biased Samplecited by 12
  18. 2022Spectral Representation Learning for Conditional Moment Modelscited by 12
  19. 2023Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounderscited by 12
  20. 2023The Fundamental Limits of Structure-Agnostic Functional Estimationcited by 12
  21. 2023Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learningcited by 11
  22. 2024Meta-Learners for Partially-Identified Treatment Effects Across Multiple Environmentscited by 11
  23. 2021Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learningcited by 10
  24. 2022Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiencycited by 10
  25. 2024Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learnercited by 10
  26. 2025Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Datacited by 10
  27. 2025TabPFN: One Model to Rule Them All?cited by 10
  28. 2021A Simple and General Debiased Machine Learning Theorem with Finite Sample Guaranteescited by 9
  29. 2021Sparsity in Partially Controllable Linear Systemscited by 9
  30. 2021Inverse-Weighted Survival Gamescited by 8
  31. 2023Source Condition Double Robust Inference on Functionals of Inverse Problemscited by 8
  32. 2024DoubleMLDeep: Estimation of Causal Effects with Multimodal Datacited by 8
  33. 2021Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effectscited by 7
  34. 2022Stability and Risk Bounds of Iterative Hard Thresholdingcited by 7
  35. 2022Robust Design and Evaluation of Predictive Algorithms under Unobserved Confoundingcited by 7
  36. 2023Proximal Causal Learning of Conditional Average Treatment Effectscited by 7
  37. 2024Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learningcited by 7
  38. 2025Treatment Effect Estimation for Optimal Decision-Makingcited by 7

50 most cited of 150 All 150 (JSON)