Corpus ID: 44110630

On GANs and GMMs

@inproceedings{Richardson2018OnGA,
  title={On GANs and GMMs},
  author={Eitan Richardson and Yair Weiss},
  booktitle={NeurIPS},
  year={2018}
}
  • Eitan Richardson, Yair Weiss
  • Published in NeurIPS 2018
  • Computer Science
  • A longstanding problem in machine learning is to find unsupervised methods that can learn the statistical structure of high dimensional signals. In recent years, GANs have gained much attention as a possible solution to the problem, and in particular have shown the ability to generate remarkably realistic high resolution sampled images. At the same time, many authors have pointed out that GANs may fail to model the full distribution ("mode collapse") and that using the learned models for… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    32
    Twitter Mentions

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 13 CITATIONS

    GDPP: Learning Diverse Generations Using Determinantal Point Process

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    A Bayes-Optimal View on Adversarial Examples

    VIEW 3 EXCERPTS
    CITES METHODS

    Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis

    VIEW 3 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Image-Adaptive GAN based Reconstruction

    VIEW 1 EXCERPT
    CITES BACKGROUND

    A RAD approach to deep mixture models

    VIEW 1 EXCERPT
    CITES METHODS

    ATTRIBUTE GAUSSIAN MIXTURE MODELLING

    • 2019
    VIEW 3 EXCERPTS
    CITES METHODS

    FMRI Data Augmentation Via Synthesis

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Graph-based Discriminators: Sample Complexity and Expressiveness

    VIEW 1 EXCERPT
    CITES METHODS

    Orthogonal Wasserstein GANs

    VIEW 1 EXCERPT
    CITES METHODS

    Privacy-preserving data sharing via probabilistic modelling

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 41 REFERENCES

    Deep Learning Face Attributes in the Wild

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    Improved Training of Wasserstein GANs

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Wasserstein Generative Adversarial Networks

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Latent Variable Models and Factor Analysis

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Are GANs Created Equal? A Large-Scale Study

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Reading Digits in Natural Images with Unsupervised Feature Learning

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL