mlsanityData to 14 Oct 2026

A Kernel Test for Causal Association via Noise Contrastive Backdoor Adjustment

arXiv 2111.13226 ↗First posted 25 Nov 2021stat.ME stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

Causal inference grows increasingly complex as the number of confounders increases. Given treatments X, confounders Z and outcomes Y, we develop a non-parametric method to test the textitdo-null hypothesis H0:; p(y|it do(X=x))=p(y) against the general alternative. Building on the Hilbert Schmidt Independence Criterion (HSIC) for marginal independence testing, we propose backdoor-HSIC (bd-HSIC) and demonstrate that it is calibrated and has power for both binary and continuous treatments under a large number of confounders. Additionally, we establish convergence properties of the estimators of covariance operators used in bd-HSIC. We investigate the advantages and disadvantages of bd-HSIC against parametric tests as well as the importance of using the do-null testing in contrast to marginal independence testing or conditional independence testing. A complete implementation can be found at hyperlinkhttps://github.com/MrHuff/kgformulatexttthttps://github.com/MrHuff/kgformula.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 13 of its 39 references that are in the map. First posted on arXiv 25 Nov 2021.

Builds on

13 of 39 references.

References · 13

  1. 2015Variational Inference with Normalizing Flowscited by 2,170
  2. 2018Which Training Methods for GANs do actually Converge?cited by 679
  3. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
  4. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 364
  5. 2019Causality matters in medical imagingcited by 193
  6. 2020Telescoping Density-Ratio Estimationcited by 108
  7. 2017Approximate Kernel-based Conditional Independence Tests for Fast Non-Parametric Causal Discoverycited by 76
  8. 2017Nested Markov Properties for Acyclic Directed Mixed Graphscited by 39
  9. 2016Large-Scale Kernel Methods for Independence Testingcited by 32
  10. 2021Parameterizing and Simulating from Causal Modelscited by 9
  11. 2013Estimation of Effects of Sequential Treatments by Reparameterizing Directed Acyclic Graphscited by 6
  12. 2021Revisiting the g-null paradoxcited by 3
1 more
  1. 2019A quantile-based g-computation approach to addressing the effects of exposure mixturescited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2024An Overview of Causal Inference using Kernel Embeddingscited by 6
  2. 2025ActiveCQ: Active Estimation of Causal Quantitiescited by 1
  3. 2025RI-Loss: A Learnable Residual-Informed Loss for Time Series Forecastingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Fast Kernel-based Conditional Independence test with Application to Causal Discovery
  2. 2023High Dimensional Causal Inference with Variational Backdoor Adjustment
  3. 2022Partial Identification with Noisy Covariates: A Robust Optimization Approach
  4. 2025Causal Additive Models with Unobserved Causal Paths and Backdoor Paths
  5. 2023Diffusion Model in Causal Inference with Unmeasured Confounders
  6. 2025Partially Functional Dynamic Backdoor Diffusion-based Causal Model
  7. 2025Stress-Testing Causal Claims via Cardinality Repairs
  8. 2026ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding