A Conditional Distribution Equality Testing Framework using Deep Generative Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Siming, Wang, Tong, Lan, Meifang, Lin, Yuanyuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909925201936384
author Zheng, Siming
Wang, Tong
Lan, Meifang
Lin, Yuanyuan
author_facet Zheng, Siming
Wang, Tong
Lan, Meifang
Lin, Yuanyuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17729
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Conditional Distribution Equality Testing Framework using Deep Generative Learning
Zheng, Siming
Wang, Tong
Lan, Meifang
Lin, Yuanyuan
Machine Learning
Statistics Theory
Methodology
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.
title A Conditional Distribution Equality Testing Framework using Deep Generative Learning
topic Machine Learning
Statistics Theory
Methodology
url https://arxiv.org/abs/2509.17729