New framework uses counterfactuals to explain deep two-sample test results

Researchers have developed a new framework for deep two-sample testing that uses counterfactual explanations to identify features driving distributional differences. The method combines a diffusion autoencoder with a pre-trained deep two-sample test model to generate edits that move samples closer to a target distribution. This approach provides interpretable evidence of group differences by showing how specific feature changes affect statistical significance, as demonstrated on synthetic data and MRI cohorts. AI

IMPACT Provides a novel method for interpreting the feature-level drivers of distributional differences detected by deep learning models in statistical tests.

RANK_REASON This is a research paper detailing a new methodology for statistical testing. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv stat.ML →

• arXiv
• Counterfactual Explanations for Deep Two-Sample Testing

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →