Co-Generation with GANs using AIS based HMC

10/31/2019
by   Tiantian Fang, et al.
16

Inferring the most likely configuration for a subset of variables of a joint distribution given the remaining ones - which we refer to as co-generation - is an important challenge that is computationally demanding for all but the simplest settings. This task has received a considerable amount of attention, particularly for classical ways of modeling distributions like structured prediction. In contrast, almost nothing is known about this task when considering recently proposed techniques for modeling high-dimensional distributions, particularly generative adversarial nets (GANs). Therefore, in this paper, we study the occurring challenges for co-generation with GANs. To address those challenges we develop an annealed importance sampling based Hamiltonian Monte Carlo co-generation algorithm. The presented approach significantly outperforms classical gradient based methods on a synthetic and on the CelebA and LSUN datasets.

READ FULL TEXT

page 7

page 8

page 15

page 16

page 17

research
06/05/2023

Structured Voronoi Sampling

Recently, there has been a growing interest in the development of gradie...
research
04/30/2020

Generative Adversarial Networks (GANs): Challenges, Solutions, and Future Directions

Generative Adversarial Networks (GANs) is a novel class of deep generati...
research
10/14/2020

Conditional Monte Carlo revisited

Conditional Monte Carlo refers to sampling from the conditional distribu...
research
08/08/2017

Parametric Adversarial Divergences are Good Task Losses for Generative Modeling

Generative modeling of high dimensional data like images is a notoriousl...
research
04/09/2023

Distributed Conditional GAN (discGAN) For Synthetic Healthcare Data Generation

In this paper, we propose a distributed Generative Adversarial Networks ...
research
11/29/2018

On the Implicit Assumptions of GANs

Generative adversarial nets (GANs) have generated a lot of excitement. D...
research
08/09/2018

User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks

Scribble colors based line art colorization is a challenging computer vi...

Please sign up or login with your details

Forgot password? Click here to reset