Understanding Disentangling in VAEs, Christopher P. Burgess, Loïc Matthey, Nicholas Watters, Dustin J. Brady, Arka Pal, Gabriel Dalcin, Irina Higgins, and Alexander Lerchner, 2018Advances in Neural Information Processing Systems (NeurIPS)DOI: 10.48550/arXiv.1804.03599 - 提供了关于VAE及其变体如何实现解耦表示的分析,检查了正则化和数据集特性的影响。
Deep Variational Information Bottleneck, Alexander A. Alemi, Ian Fischer, Joshua V. Dillon, Kevin Murphy, 2018International Conference on Learning Representations (ICLR) (International Conference on Learning Representations (ICLR)) - 将深度变分自编码器与信息瓶颈理论联系起来,为KL项如何在潜在空间中促进高效信息压缩提供了理论解释。