论文标题
通过离散的无向图形模型的集合进行对抗学习的推断
Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
论文作者
论文摘要
无向图形模型是随机变量上关节概率分布的紧凑表示。为了解决感兴趣的推理任务，可以使用经验风险最小化训练任意拓扑的图形模型。但是，为了解决训练中未看到的推理任务，这些模型（EGM）通常需要重新训练。取而代之的是，我们提出了一个推理 - 反向对抗训练框架，该培训框架产生了图形模型（AGM）的绝大部分集合。优化集合以在GAN框架内生成数据，并使用这些模型的有限子集执行推理。 AGM与EGM相当地对后者专门优化的推理任务执行。最重要的是，与EGMS相比，AGM显示出对未见推理任务的概括，以及Gibbsnet和VAEAC等深层神经体系结构，允许任意调节。最后，AGM允许快速数据采样，具有EGM的Gibbs采样竞争。
Undirected graphical models are compact representations of joint probability distributions over random variables. To solve inference tasks of interest, graphical models of arbitrary topology can be trained using empirical risk minimization. However, to solve inference tasks that were not seen during training, these models (EGMs) often need to be re-trained. Instead, we propose an inference-agnostic adversarial training framework which produces an infinitely-large ensemble of graphical models (AGMs). The ensemble is optimized to generate data within the GAN framework, and inference is performed using a finite subset of these models. AGMs perform comparably with EGMs on inference tasks that the latter were specifically optimized for. Most importantly, AGMs show significantly better generalization to unseen inference tasks compared to EGMs, as well as deep neural architectures like GibbsNet and VAEAC which allow arbitrary conditioning. Finally, AGMs allow fast data sampling, competitive with Gibbs sampling from EGMs.
