We introduce the Generalized Energy Based Model (GEBM) for generative modelling. These models combine two trained components: a base distribution (generally an implicit model), which can learn the support of data with low intrinsic dimension in a high dimensional space; and an energy function, to refine the probability mass on the learned support. Both the energy function and base jointly constitute the final model, unlike GANs, which retain only the base distribution (the "generator"). GEBMs are trained by alternating between learning the energy and the base. We show that both training stages are well-defined: the energy is learned by maximising a generalized likelihood, and the resulting energy-based loss provides informative gradients for learning the base. Samples from the posterior on the latent space of the trained model can be obtained via MCMC, thus finding regions in this space that produce better quality samples. Empirically, the GEBM samples on image-generation tasks are of much better quality than those from the learned generator alone, indicating that all else being equal, the GEBM will outperform a GAN of the same complexity. When using normalizing flows as base measures, GEBMs succeed on density modelling tasks, returning comparable performance to direct maximum likelihood of the same networks.
翻译:我们采用通用能源基础模型(GEBM)进行基因建模,这些模型结合了两个经过培训的构成部分:基础分布(一般为隐含模型),可以学习高维空间内低内在层面数据的支持;以及能源功能,以完善学习支持的概率质量;能源功能和基础共同构成最后模型,不同于仅保留基分布(“发电机”)的GANs,GEBMs通过在学习能源和基地之间交替进行培训;我们表明,两个培训阶段都是明确界定的:能源是通过实现普遍可能性最大化而学的,由此造成的能源损失为学习基础提供了信息梯度;通过MCMC可以获得关于培训模型潜在空间的样本,从而在这个空间中找到能够产生质量更好的样本的区域;有规律地说,关于图像生成任务的GEBMs样本的质量比仅仅从学习的发电机中获得的样本要高得多,这表明,除了其他所有培训阶段一样,GBMM将超越GAN的复杂度。在使用正常流动作为基础测量时,将GBMs成功进行相同的模拟。