mlsanityData to 14 Oct 2026

A Conditional Distribution Equality Testing Framework using Deep Generative Learning

arXiv 2509.17729 ↗First posted 22 Sep 2025cs.LG math.ST stat.MEcited by 1

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a general framework for testing the conditional distribution equality in a two-sample problem, which is most relevant to covariate shift and causal discovery. Our framework is built on neural network-based generative methods and sample splitting techniques by transforming the conditional testing problem into an unconditional one. We introduce the generative classification accuracy-based conditional distribution equality test (GCA-CDET) to illustrate the proposed framework. We establish the convergence rate for the learned generator by deriving new results related to the recently-developed offset Rademacher complexity and prove the testing consistency of GCA-CDET under mild conditions.Empirically, we conduct numerical studies including synthetic datasets and two real-world datasets, demonstrating the effectiveness of our approach. Additional discussions on the optimality of the proposed framework are provided in the online supplementary material.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 50 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

23 of 50 references.

References · 23

  1. 2022Flow Matching for Generative Modelingcited by 5,702
  2. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  3. 2015On Wasserstein Two Sample Testing and Related Families of Nonparametric Testscited by 166
  4. 2020Conformal Inference of Counterfactuals and Individual Treatment Effectscited by 151
  5. 2018Invariance, Causality and Robustnesscited by 123
  6. 2020Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimationcited by 45
  7. 2015Learning with Square Loss: Localization through Offset Rademacher Complexitycited by 38
  8. 2019Conditional Independence Testing using Generative Adversarial Networkscited by 36
  9. 2022A new similarity measure for covariate shift with applications to nonparametric regressioncited by 33
  10. 2024Score-based Causal Representation Learning: Linear and General Transformationscited by 27
  11. 2020Double Generative Adversarial Networks for Conditional Independence Testingcited by 22
  12. 2022Prediction Sets Adaptive to Unknown Covariate Shiftcited by 22
11 more
  1. 2020A Two-Sample Conditional Distribution Test Using Conformal Prediction and Weighted Rank Sumcited by 19
  2. 2023Environment Invariant Linear Least Squarescited by 17
  3. 2023Derandomized Novelty Detection with FDR Control via Conformal E-valuescited by 15
  4. 2022Derandomized knockoffs: leveraging e-values for false discovery rate controlcited by 12
  5. 2020Derandomizing Knockoffscited by 9
  6. 2023Testing for the Markov Property in Time Series via Deep Conditional Generative Learningcited by 9
  7. 2025Conditional Data Synthesis Augmentationcited by 8
  8. 2024Doubly Robust Conditional Independence Testing with Generative Neural Networkscited by 7
  9. 2024De-Biased Two-Sample U-Statistics With Application To Conditional Distribution Testingcited by 6
  10. 2023Efficient and Multiply Robust Risk Estimation under General Forms of Dataset Shiftcited by 5
  11. 2023Model-based causal feature selection for general response typescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ANGLE: Angular Neural Generative Learning via Engressioncited by 0