HackerPapers

arXiv:1701.07875stat.ML

Wasserstein GAN

Martin Arjovsky, Soumith Chintala, Léon Bottou

Abstract

We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Furthermore, we show that the corresponding optimization problem is sound, and provide extensive theoretical work highlighting the deep connections to other distances between distributions.

arXiv comments
Journal reference
DOI
Subjects
stat.MLMachine Learning (Statistics) cs.LGMachine Learning

On Hacker News

Linked by 5 identifiable commenters in 5 comments across 5 threads, from May 2017 to Apr 2019. Found in 2 HN submissions from Jan 2017 to Feb 2017. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. Open Questions about Generative Adversarial Networks 1 comment

    • Hmm, I'm not sure what you mean by applicable loss functions? I'll answer what I think you're asking and you can tell me if I got it wrong: There's been a lot of effort spent on coming up with different loss functions for GANs, but https://arxiv.org/abs/1711.10337 shows that…

      tasdfqwer0897View on HNParent context

  2. Machine learning is not just glorified statistics 1 comment

    • Quote: “One of our assigned projects was to implement and train a Wasserstein GAN in TensorFlow. At this point, I had taken only an introductory statistics class that was a required general elective, and then promptly forgotten most of it. Needless to say, my statistical skills…

      phonebucketView on HNParent context

  3. Building a Content-Based Search Engine IV: Earth Mover's Distance 1 comment

    • There is a paper that indicates Earth mover, aka Wasserstein-1 is better for convergence of GANs: https://arxiv.org/pdf/1701.07875.pdf I tried it out on one of the Udacity Deep learning assignments using the Wasserstein loss functions built into tensorflow. I was unsuccessful in…

      SteveJSView on HNParent context

  4. Do I really have to cite an arXiv paper? 1 comment

    • The kind of math that would be necessary to understand papers like [1][2][3][4]. [1]: https://arxiv.org/abs/1703.04933 [2]: https://arxiv.org/abs/1701.07875 [3]: https://arxiv.org/abs/1706.01350 [4]: https://arxiv.org/abs/1512.04860

      backpropagandaView on HNParent context

  5. Sorting Two Tons of Lego, the Software Side 1 comment

    • It's not so much that there's just one or two specific results, but rather that there's just far more researchers working on this now, and quite a few are working on more theoretical stuff. Sometimes, that theory results in really practical outcomes - a good example would be…

      jph00View on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.