论文标题
部分可观测时空混沌系统的无模型预测
Three Variations on Variational Autoencoders
论文作者
论文摘要
变异自动编码器（VAE）是一类生成概率的潜在可变性模型，该模型是基于已知数据而设计的。我们通过引入第二个参数化的编码器/解码器对，并为一个变体提供一个额外的固定编码器来开发VAE的三个变体。编码器/解码器的参数应通过神经网络学习。固定编码器是通过概率-PCA获得的。将变化与原始VAE的近似值（ELBO）近似值进行比较。一种变异导致证据上限（EUBO），可以与原始Elbo结合使用，以询问VAE的收敛性。
Variational autoencoders (VAEs) are one class of generative probabilistic latent-variable models designed for inference based on known data. We develop three variations on VAEs by introducing a second parameterized encoder/decoder pair and, for one variation, an additional fixed encoder. The parameters of the encoders/decoders are to be learned with a neural network. The fixed encoder is obtained by probabilistic-PCA. The variations are compared to the Evidence Lower Bound (ELBO) approximation to the original VAE. One variation leads to an Evidence Upper Bound (EUBO) that can be used in conjunction with the original ELBO to interrogate the convergence of the VAE.
