论文标题
与学生T-Prior的变异自动编码器
Variational auto-encoders with Student's t-prior
论文作者
论文摘要
我们提出了一个差异自动编码器(VAE)的新结构,并具有弱信息的多元学生T分布。在建议的模型中,所有分布参数均经过训练,从而使基础数据分布更加稳定。我们在两个实验中使用了时尚流行数据,将提出的VAE与标准高斯先验进行了比较。这两个实验均显示了使用学生的T-Prior分布对VAE进行更好的图像重建。
We propose a new structure for the variational auto-encoders (VAEs) prior, with the weakly informative multivariate Student's t-distribution. In the proposed model all distribution parameters are trained, thereby allowing for a more robust approximation of the underlying data distribution. We used Fashion-MNIST data in two experiments to compare the proposed VAEs with the standard Gaussian priors. Both experiments showed a better reconstruction of the images with VAEs using Student's t-prior distribution.