MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets

Pierre-Alexandre Mattei, Jes Frellsen

Abstract

We consider the problem of handling missing data with deep latent variable models (DLVMs). First, we present a simple technique to train DLVMs when the training set contains missing-at-random data....
BibTeX
@inproceedings{mattei2019miwae,
  author = {Pierre-Alexandre Mattei and Jes Frellsen},
  title = {{MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets}},
  booktitle = {International Conference on Machine Learning},
  year = {2019},
}
Figure