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

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed