论文标题
可扩展的高斯流程变量自动编码器
Scalable Gaussian Process Variational Autoencoders
论文作者
论文摘要
传统的变异自动编码器由于使用分解的先验而无法建模数据点之间的相关性。通过GP-VAE的摊销高斯工艺推断已导致这方面的显着改善，但仍受到精确GP推断的内在复杂性的抑制。我们通过原则上的稀疏推理方法来提高这些方法的可伸缩性。我们提出了一种新的可扩展GP-VAE模型，该模型在运行时和内存足迹方面胜过现有方法，易于实现，并允许对所有组件进行联合端到端优化。
Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors. Amortized Gaussian process inference through GP-VAEs has led to significant improvements in this regard, but is still inhibited by the intrinsic complexity of exact GP inference. We improve the scalability of these methods through principled sparse inference approaches. We propose a new scalable GP-VAE model that outperforms existing approaches in terms of runtime and memory footprint, is easy to implement, and allows for joint end-to-end optimization of all components.
