Corpus ID: 3350443

AdaGAN: Boosting Generative Models

@inproceedings{Tolstikhin2017AdaGANBG,
  title={AdaGAN: Boosting Generative Models},
  author={I. Tolstikhin and S. Gelly and O. Bousquet and Carl-Johann Simon-Gabriel and B. Sch{\"o}lkopf},
  booktitle={NIPS},
  year={2017}
}
  • I. Tolstikhin, S. Gelly, +2 authors B. Schölkopf
  • Published in NIPS 2017
  • Computer Science, Mathematics
  • Generative Adversarial Networks (GAN) are an effective method for training generative models of complex data such as natural images. However, they are notoriously hard to train and can suffer from the problem of missing modes where the model is not able to produce examples in certain regions of the space. We propose an iterative procedure, called AdaGAN, where at every step we add a new component into a mixture model by running a GAN algorithm on a re-weighted sample. This is inspired by… CONTINUE READING
    146 Citations
    An Online Learning Approach to Generative Adversarial Networks
    • 61
    • PDF
    A Framework of Composite Functional Gradient Methods for Generative Adversarial Models
    • R. Johnson, T. Zhang
    • Computer Science, Medicine
    • IEEE Transactions on Pattern Analysis and Machine Intelligence
    • 2021
    • 3
    • PDF
    Boundary-Seeking Generative Adversarial Networks
    • 100
    • PDF
    Composite Functional Gradient Learning of Generative Adversarial Models
    • 7
    • PDF
    Boosting Generative Models by Leveraging Cascaded Meta-Models
    • 1
    • PDF
    Latent Dirichlet Allocation in Generative Adversarial Networks
    • 4
    • Highly Influenced
    • PDF
    Deconstructing Generative Adversarial Networks
    • 10
    • PDF
    Generative Adversarial Networks: An Overview
    • 400
    • PDF
    MGAN: TRAINING GENERATIVE ADVERSARIAL NETS
    • 2017
    • PDF
    On the regularization of Wasserstein GANs
    • 102
    • PDF

    References

    SHOWING 1-10 OF 24 REFERENCES
    Generative Adversarial Nets
    • 20,850
    • Highly Influential
    • PDF
    Mode Regularized Generative Adversarial Networks
    • 313
    • Highly Influential
    • PDF
    Ensembles of Generative Adversarial Networks
    • 36
    • PDF
    Improved Techniques for Training GANs
    • 4,055
    • PDF
    f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
    • 874
    • PDF
    On the Quantitative Analysis of Decoder-Based Generative Models
    • 174
    • PDF
    Boosted Generative Models
    • 27
    • PDF
    Unrolled Generative Adversarial Networks
    • 569
    • Highly Influential
    • PDF
    Learning Generative Models via Discriminative Approaches
    • Zhuowen Tu
    • Computer Science
    • 2007 IEEE Conference on Computer Vision and Pattern Recognition
    • 2007
    • 100
    • PDF