Co-Generation with GANs using AIS based HMC
This addresses a computationally demanding challenge in machine learning for researchers and practitioners working with GANs, though it is incremental as it builds on existing techniques.
The paper tackles the problem of co-generation with GANs, which involves inferring likely variable configurations in high-dimensional distributions, and presents an annealed importance sampling based Hamiltonian Monte Carlo algorithm that significantly outperforms classical gradient-based methods on synthetic, CelebA, and LSUN datasets.
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.