Yunus Saatci
Yunus Saatci is a senior research scientist with Uber AI Labs.
Engineering Blog Articles
How to Get a Better GAN (Almost) for Free: Introducing the Metropolis-Hastings GAN
Metropolis-Hastings Generative Adversarial Networks (GANs) leverage the discriminator to pick better samples from the generator after ML model training is done.
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
Bayesian Generative Adversarial Networks
Y. Saatchi, A. Wilson
Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. We present a practical Bayesian formulation for unsupervised and semi-supervised learning with GANs. [...] [PDF]
Advances in Neural Information Processing Systems (NeurIPS), 2017
Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. We present a practical Bayesian formulation for unsupervised and semi-supervised learning with GANs. [...] [PDF]
Advances in Neural Information Processing Systems (NeurIPS), 2017
