arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.08205stat.MLcs.LG
收藏

基于潜空间能量的先验模型学习

Learning Latent Space Energy-Based Prior Model

University of California, Los Angeles(加州大学洛杉矶分校);Stevens Institute of Technology(斯蒂文斯理工学院)

Bo Pang, Tian Han, Erik Nijkamp, Song-Chun Zhu, Ying Nian Wu

摘要:

我们建议在发电机模型的潜在空间中学习基于能量的模型(EBM),这样EBM就可以作为发电机模型自顶向下网络上的先验模型。潜在空间EBM和自上而下的网络都可以通过极大似然联合学习,这涉及从潜在向量的先验分布和后验分布进行短期MCMC采样。由于潜在空间的低维性和自顶向下网络的表达能力,潜在空间中的简单EBM可以有效地捕获数据中的错误,并且潜在空间中的MCMC采样是有效的并且混合良好。我们表明,学习模型在图像和文本生成和异常检测方面表现出很强的性能。单页代码可以在补充材料中找到。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑