论文标题
跨自动编码器体系结构的分配数据的几何不稳定性
Geometric instability of out of distribution data across autoencoder architecture
论文作者
论文摘要
我们研究了一个经过MNIST培训的自动编码器家族所学的地图，并根据十个不同的分布来对像素值随机选择创建的十个不同数据集进行了评估。具体而言，我们研究了每个培训和评估点自动编码器的重量矩阵定义的雅各布人的特征值。对于足够高的潜在维度，我们发现每个自动编码器都将所有评估数据集重建为相似的\ emph {generalized targual}，但是此重建为“自动编码器”的重建\ emph {generalized cartarion}会更改。特征值分析表明，即使重建的图像似乎是所有分布数据集的MNIST字符，并非所有人都具有接近MNIST字符的潜在表示的潜在表示。总而言之，特征值分析表明，自动编码器的几何不稳定性既是分布输入的函数，又在同一集合输入上跨体系结构。
We study the map learned by a family of autoencoders trained on MNIST, and evaluated on ten different data sets created by the random selection of pixel values according to ten different distributions. Specifically, we study the eigenvalues of the Jacobians defined by the weight matrices of the autoencoder at each training and evaluation point. For high enough latent dimension, we find that each autoencoder reconstructs all the evaluation data sets as similar \emph{generalized characters}, but that this reconstructed \emph{generalized character} changes across autoencoder. Eigenvalue analysis shows that even when the reconstructed image appears to be an MNIST character for all out of distribution data sets, not all have latent representations that are close to the latent representation of MNIST characters. All told, the eigenvalue analysis demonstrated a great deal of geometric instability of the autoencoder both as a function on out of distribution inputs, and across architectures on the same set of inputs.
