ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2208.08579
16
2

DIET: Conditional independence testing with marginal dependence measures of residual information

18 August 2022
Mukund Sudarshan
A. Puli
Wesley Tansey
Rajesh Ranganath
ArXivPDFHTML
Abstract

Conditional randomization tests (CRTs) assess whether a variable xxx is predictive of another variable yyy, having observed covariates zzz. CRTs require fitting a large number of predictive models, which is often computationally intractable. Existing solutions to reduce the cost of CRTs typically split the dataset into a train and test portion, or rely on heuristics for interactions, both of which lead to a loss in power. We propose the decoupled independence test (DIET), an algorithm that avoids both of these issues by leveraging marginal independence statistics to test conditional independence relationships. DIET tests the marginal independence of two random variables: F(x∣z)F(x \mid z)F(x∣z) and F(y∣z)F(y \mid z)F(y∣z) where F(⋅∣z)F(\cdot \mid z)F(⋅∣z) is a conditional cumulative distribution function (CDF). These variables are termed "information residuals." We give sufficient conditions for DIET to achieve finite sample type-1 error control and power greater than the type-1 error rate. We then prove that when using the mutual information between the information residuals as a test statistic, DIET yields the most powerful conditionally valid test. Finally, we show DIET achieves higher power than other tractable CRTs on several synthetic and real benchmarks.

View on arXiv
Comments on this paper