Timezone: »
Poster
Banach Wasserstein GAN
Jonas Adler · Sebastian Lunz
Wasserstein Generative Adversarial Networks (WGANs) can be used to generate realistic samples from complicated image distributions. The Wasserstein metric used in WGANs is based on a notion of distance between individual images, which induces a notion of distance between probability distributions of images. So far the community has considered $\ell^2$ as the underlying distance. We generalize the theory of WGAN with gradient penalty to Banach spaces, allowing practitioners to select the features to emphasize in the generator. We further discuss the effect of some particular choices of underlying norms, focusing on Sobolev norms. Finally, we demonstrate a boost in performance for an appropriate choice of norm on CIFAR-10 and CelebA.
Author Information
Jonas Adler (KTH - Royal Institute of Technology)
I’m a Research Scientist at Elekta, pursuing a PhD in Applied Mathematics working under the supervision of Ozan Öktem. I do research in inverse problems and machine learning, especially focusing on the intersection between model-driven and data-driven methods. Organizing [DLIP2019](https://sites.google.com/view/dlip2019).
Sebastian Lunz (University of Cambridge)
More from the Same Authors
-
2022 Workshop: Machine Learning in Structural Biology Workshop »
Roshan Rao · Jonas Adler · Namrata Anand · John Ingraham · Sergey Ovchinnikov · Ellen Zhong -
2021 : Jonas Adler »
Jonas Adler -
2018 : Poster session »
David Zeng · Marzieh S. Tahaei · Shuai Chen · Felix Meister · Meet Shah · Anant Gupta · Ajil Jalal · Eirini Arvaniti · David Zimmerer · Konstantinos Kamnitsas · Pedro Ballester · Nathaniel Braman · Udaya Kumar · Sil C. van de Leemput · Junaid Qadir · Hoel Kervadec · Mohamed Akrout · Adrian Tousignant · Matthew Ng · Raghav Mehta · Miguel Monteiro · Sumana Basu · Jonas Adler · Adrian Dalca · Jizong Peng · Sungyeob Han · Xiaoxiao Li · Karthik Gopinath · Joseph Cheng · Bogdan Georgescu · Kha Gia Quach · Karthik Sarma · David Van Veen -
2018 : Oral session I »
Jonas Adler · Ajil Jalal · Joseph Cheng -
2018 Poster: Adversarial Regularizers in Inverse Problems »
Sebastian Lunz · Carola-Bibiane Schönlieb · Ozan Öktem -
2017 : 6 x 3 minutes spotlights »
Rémi Flamary · Yongxin Chen · Napat Rujeerapaiboon · Jonas Adler · John Lee · Lucas R Roberts