Arbitrarily-conditioned Data ImputationDownload PDF

16 Oct 2019 (modified: 15 Dec 2019)AABI 2019 Symposium Blind SubmissionReaders: Everyone
  • Keywords: data imputation, variational autoencoder, normalizing flow
  • TL;DR: We propose an arbitrarily-conditioned data imputation framework built upon variational autoencoders and normalizing flows
  • Abstract: In this paper, we propose an arbitrarily-conditioned data imputation framework built upon variational autoencoders and normalizing flows. The proposed model is capable of mapping any partial data to a multi-modal latent variational distribution. Sampling from such a distribution leads to stochastic imputation. Preliminary evaluation on MNIST dataset shows promising stochastic imputation conditioned on partial images as input.
0 Replies

Loading