Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy

TL;DR

This paper introduces an optimized maximum mean discrepancy (MMD) method to improve the discrimination and evaluation of generative models, enhancing the interpretability and effectiveness of model criticism in unsupervised learning.

Contribution

It develops an optimized MMD approach for better sample comparison and model evaluation, applicable to generative adversarial networks and other unsupervised learning models.

Findings

Optimized MMD improves test power for distribution comparison.

Enhanced interpretability of model-data distribution differences.

Effective for evaluating generative models even with indistinguishable samples.

Abstract

We propose a method to optimize the representation and distinguishability of samples from two probability distributions, by maximizing the estimated power of a statistical test based on the maximum mean discrepancy (MMD). This optimized MMD is applied to the setting of unsupervised learning by generative adversarial networks (GAN), in which a model attempts to generate realistic samples, and a discriminator attempts to tell these apart from data samples. In this context, the MMD may be used in two roles: first, as a discriminator, either directly on the samples, or on features of the samples. Second, the MMD can be used to evaluate the performance of a generative model, by testing the model's samples against a reference data set. In the latter role, the optimized MMD is particularly helpful, as it gives an interpretable indication of how the model and data distributions differ, even in cases where individual model samples are not easily distinguished either by eye or by classifier.