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.
翻译:考虑到其余的(我们称为共同生成),估计联合分布的一组变数最有可能的配置是一个重大挑战,除了最简单的设置外,对所有人来说都是计算上的要求。这项任务得到了相当多的关注,特别是典型的模型分布方式,如结构化预测。相反,在考虑最近提出的高维分布模型,特别是基因对抗网(GANs)技术时,几乎对这项任务几乎一无所知。因此,在本文中,我们研究了与GANs共同生成的挑战。为了应对这些挑战,我们开发了以汉密尔顿·蒙特卡洛共同生成算法为基础的麻醉重要取样方法。所提出的方法大大优于以合成和CelebA和LSUN数据集为基础的典型梯度方法。