论文标题
学习潜在的基于节能的先验模型
Learning Latent Space Energy-Based Prior Model
论文作者
论文摘要
我们建议在生成器模型的潜在空间中学习基于能量的模型（EBM），以便EBM充当站在生成器模型自上而下网络的先前模型。潜在空间EBM和自上而下的网络都可以通过最大可能性共同学习，这涉及从潜在矢量的先前和后分布中进行短期MCMC采样。由于潜在空间的尺寸较低和自上而下的网络的表现力，因此潜在空间中的简单EBM可以有效地捕获数据的规律性，并且潜在空间中的MCMC采样有效，可以很好地混合。我们表明，学到的模型在图像和文本生成和异常检测方面表现出强烈的性能。一页代码可以在补充材料中找到。
We propose to learn energy-based model (EBM) in the latent space of a generator model, so that the EBM serves as a prior model that stands on the top-down network of the generator model. Both the latent space EBM and the top-down network can be learned jointly by maximum likelihood, which involves short-run MCMC sampling from both the prior and posterior distributions of the latent vector. Due to the low dimensionality of the latent space and the expressiveness of the top-down network, a simple EBM in latent space can capture regularities in the data effectively, and MCMC sampling in latent space is efficient and mixes well. We show that the learned model exhibits strong performances in terms of image and text generation and anomaly detection. The one-page code can be found in supplementary materials.
