Journal
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)
Volume -, Issue -, Pages 3325-3329Publisher
IEEE
DOI: 10.1109/ICASSP39728.2021.9414454
Keywords
WGANs; Bregman cost functions; image and signal processing; wireless communication; fast and stable convergence
Ask authors/readers for more resources
This paper introduces a new class of Relaxed Wasserstein distances by generalizing Wasserstein-1 distance with Bregman cost functions. Experiments demonstrate that Relaxed WGANs with Kullback-Leibler cost function outperform other competing approaches in terms of statistical flexibility and efficient approximations.
Wasserstein Generative Adversarial Networks (WGANs) provide a versatile class of models, which have attracted great attention in various applications. However, this framework has two main drawbacks: (i) Wasserstein-1 (or Earth-Mover) distance is restrictive such that WGANs cannot always fit data geometry well; (ii) It is difficult to achieve fast training of WGANs. In this paper, we propose a new class of Relaxed Wasserstein (RW) distances by generalizing Wasserstein-1 distance with Bregman cost functions. We show that RW distances achieve nice statistical properties while not sacrificing the computational tractability. Combined with the GANs framework, we develop Relaxed WGANs (RWGANs) which are not only statistically flexible but can be approximated efficiently using heuristic approaches. Experiments on real images demonstrate that the RWGAN with Kullback-Leibler (KL) cost function outperforms other competing approaches, e.g., WGANs, even with gradient penalty.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available