2017/06/07 by Jakub M. Tomczak, Max Welling, Tomczak, Jakub M. +1 · 1 citation
Mathematics · #FOS: Computer and information sciences #Machine Learning (stat.ML) #stat.ML
paper · pdf · doi:10.48550/arxiv.1706.02326
Published at Benelearn 2017 (Eindhoven, the Netherlands)
arxiv created 2017/06/14 · arxiv updated 2017/06/15
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.