Unit testing is an important part of modern, collaborative software development. Especially as the number of project contributors grows, rigorous unit test coverage helps monitor and enforce high quality. Having a good system in place to generate test cases is …
Ryan Turner
Engineering Blog Articles
How to Get a Better GAN (Almost) for Free: Introducing the Metropolis-Hastings GAN
Generative Adversarial Networks (GANs) have achieved impressive feats in realistic image generation and image repair. Art produced by a GAN has even been sold at auction for over $400,000!
At Uber, GANs have myriad potential applications, including strengthening our …
Research Papers
Metropolis-Hastings Generative Adversarial Networks
R. Turner, J. Hung, Y. Saatci, J. Yosinski
We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs. The MH-GAN draws samples from the distribution implicitly defined by a GAN's discriminator-generator pair, as opposed to sampling in a standard GAN which draws samples from the distribution defined by the generator. [...] [PDF]
International Conference on Machine Learning (ICML), 2019
We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs. The MH-GAN draws samples from the distribution implicitly defined by a GAN's discriminator-generator pair, as opposed to sampling in a standard GAN which draws samples from the distribution defined by the generator. [...] [PDF]
International Conference on Machine Learning (ICML), 2019