Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy

arxiv(2020)

引用 1|浏览34
暂无评分
摘要
In this paper, we present a general method that can improve the sample quality of pre-trained likelihood based generative models. Our method constructs an energy function on the latent variable space that yields an energy function on samples produced by the pre-trained generative model. The energy based model is efficiently trained by maximizing the data likelihood, and after training, new samples in the latent space are generated from the energy based model and passed through the generator to producing samples in observation space. We show that using our proposed method, we can greatly improve the sample quality of popular likelihood based generative models, such as normalizing flows and VAEs, with very little computational overhead.
更多
查看译文
关键词
generative models,sampling,sample quality
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要