Ensembles of Generative Adversarial Networks for Disconnected Data

Lorenzo Luzi, Randall Balestriero, Richard Baraniuk

Keywords: GANs, ensembles, disconnected data

Abstract: Most computer vision datasets are composed of disconnected sets, such as images of different objects. We prove that distributions of this type of data cannot be represented with a continuous generative network without error, independent of the learning algorithm used. Disconnected datasets can be represented in two ways: with an ensemble of networks or with a single network using a truncated latent space. We show that ensembles are more desirable than truncated distributions for several theoretical and computational reasons. We construct a regularized optimization problem that rigorously establishes the relationships between a single continuous GAN, an ensemble of GANs, conditional GANs, and Gaussian Mixture GANs. The regularization can be computed efficiently, and we show empirically that our framework has a performance sweet spot that can be found via hyperparameter tuning. The ensemble framework provides better performance than a single continuous GAN or cGAN while maintaining fewer total parameters.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We show how ensembles of GANs are better suited than single GANs for learning distributions that generate disconnected data.

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:2006.14600/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=2E2Ro8CUn