H-divergence: A Decision-Theoretic Discrepancy Measure for Two Sample Tests

Abstract

Measuring the discrepancy between two probability distributions is a fundamental problem in machine learning and statistics. Based on ideas from decision theory, we investigate a new class of discrepancies that are based on the optimal decision loss. Two probability distributions are different if the optimal decision loss is higher on the mixture distribution than on each individual distribution. We show that this generalizes popular notions of discrepancy measurements such as the Jensen Shannon divegence and the maximum mean discrepancy. We apply our approach to two-sample tests, which evaluates whether two sets of samples come from the same distribution. On various benchmark and real datasets, we demonstrate that tests based on our generalized notion of discrepancy is able to achieve superior test power. We also apply our approach to sample quality evaluation as an alternative to the FID score, and our discrepancy ranks sample quality consistently with human intuition.

Tasks

Reproductions