Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow
arXiv: Machine Learning(2017)
摘要
In this paper, we propose a new volume-preserving flow and show that it performs similarly to the linear general normalizing flow. The idea is to enrich a linear Inverse Autoregressive Flow by introducing multiple lower-triangular matrices with ones on the diagonal and combining them using a convex combination. In the experimental studies on MNIST and Histopathology data we show that the proposed approach outperforms other volume-preserving flows and is competitive with current state-of-the-art linear normalizing flow.
更多查看译文
关键词
flow,auto-encoders
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络