Importance Weighted Autoencoders, Yuri Burda, Roger Grosse, and Ruslan Salakhutdinov, 2015International Conference on Learning Representations (ICLR) (PMLR (Proceedings of Machine Learning Research))DOI: 10.48550/arXiv.1509.00519 - 提出了重要性加权自编码器(IWAE),以提供更紧密的对数似然下界,提升了VAE的性能并减轻了后验坍缩。