Revisiting Classifier Two-Sample Tests

Abstract

The goal of two-sample tests is to assess whether two samples, $S_P\sim P^n$ and $S_Q\sim Q^m$, are drawn from the same distribution. Perhaps intriguingly, one relatively unexplored method to build two-sample tests is the use of binary classifiers. In particular, construct a dataset by pairing the $n$ examples in $S_P$ with a positive label, and by pairing the $m$ examples in $S_Q$ with a negative label. If the null hypothesis "$P=Q$" is true, then the classification accuracy of a binary classifier on a held-out subset of this dataset should remain near chance-level. As we will show, such Classifier Two-Sample Tests (C2ST) learn a suitable representation of the data on the fly, return test statistics in interpretable units, have a simple null distribution, and their predictive uncertainty allow to interpret where $P$ and $Q$ differ. The goal of this paper is to establish the properties, performance, and uses of C2ST. First, we analyze their main theoretical properties. Second, we compare their performance against a variety of state-of-the-art alternatives. Third, we propose their use to evaluate the sample quality of generative models with intractable likelihoods, such as Generative Adversarial Networks (GANs). Fourth, we showcase the novel application of GANs together with C2ST for causal discovery.

Cited by in corpus (11)

• A survey on GANs for computer vision: Recent research, analysis and taxonomy
• Testing for Outliers with Conformal p-values
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
• Methods for Quantifying Dataset Similarity: a Review, Taxonomy and Comparison
• ChartPointFlow for Topology-Aware 3D Point Cloud Generation
• Recursive Chaining of Reversible Image-to-image Translators For Face Aging
• Recent Advances of Image Steganography with Generative Adversarial Networks
• Refinable modeling for unbinned SMEFT analyses
• GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks
• A fast and effective kernel two-sample test for large-scale data