Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
Published in
International Conference on Machine Learning(2019)External Links:
TL
TL;DR
It is proved that a flow must become arbitrarily numerically noninvertible in order to approximate the target closely, and proposed Continuously Indexed Flows (CIFs) are proposed, which replace the single bijection used by normalising flows with a continuously indexed family of bijections.