A Characteristic Function Approach to Deep Implicit Generative Modeling

by   Abdul Fatir Ansari, et al.
National University of Singapore

In this paper, we formulate the problem of learning an Implicit Generative Model (IGM) as minimizing the expected distance between characteristic functions. Specifically, we match the characteristic functions of the real and generated data distributions under a suitably-chosen weighting distribution. This distance measure, which we term as the characteristic function distance (CFD), can be (approximately) computed with linear time-complexity in the number of samples, compared to the quadratic-time Maximum Mean Discrepancy (MMD). By replacing the discrepancy measure in the critic of a GAN with the CFD, we obtain a model that is simple to implement and stable to train; the proposed metric enjoys desirable theoretical properties including continuity and differentiability with respect to generator parameters, and continuity in the weak topology. We further propose a variation of the CFD in which the weighting distribution parameters are also optimized during training; this obviates the need for manual tuning and leads to an improvement in test power relative to CFD. Experiments show that our proposed method outperforms WGAN and MMD-GAN variants on a variety of unsupervised image generation benchmark datasets.


page 7

page 17

page 18

page 19

page 20


MMD GAN: Towards Deeper Understanding of Moment Matching Network

Generative moment matching network (GMMN) is a deep generative model tha...

Geometrical Insights for Implicit Generative Modeling

Learning algorithms for implicit generative models can optimize a variet...

PCF-GAN: generating sequential data via the characteristic function of measures on the path space

Generating high-fidelity time series data using generative adversarial n...

Analyze the Effects of Weighting Functions on Cost Function in the Glove Model

When dealing with the large vocabulary size and corpus size, the run-tim...

Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space

For a given image generation problem, the intrinsic image manifold is of...

On gradient regularizers for MMD GANs

We propose a principled method for gradient-based regularization of the ...

Sobolev GAN

We propose a new Integral Probability Metric (IPM) between distributions...

Code Repositories


Pytorch implementation of OCFGAN-GP (CVPR 2020, Oral).

view repo

Please sign up or login with your details

Forgot password? Click here to reset