DeepAI AI Chat
Log In Sign Up

Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy

by   Dougal J. Sutherland, et al.
Carnegie Mellon University

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.


Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks

Despite remarkable performance in producing realistic samples, Generativ...

New Losses for Generative Adversarial Learning

Generative Adversarial Networks (Goodfellow et al., 2014), a major break...

Associative Adversarial Networks

We propose a higher-level associative memory for learning adversarial ne...

A Simple Generative Network

Generative neural networks are able to mimic intricate probability distr...

A Characteristic Function Approach to Deep Implicit Generative Modeling

In this paper, we formulate the problem of learning an Implicit Generati...

Interpretable Distribution Features with Maximum Testing Power

Two semimetrics on probability distributions are proposed, given as the ...

Code Repositories


Learning kernels to maximize the power of MMD tests

view repo