ICML 2021spotlight63 citations

Composing Normalizing Flows for Inverse Problems

Jay Whang, Erik Lindgren, Alex Dimakis

Abstract

Given an inverse problem with a normalizing flow prior, we wish to estimate the distribution of the underlying signal conditioned on the observations. We approach this problem as a task of conditional inference on the pre-trained unconditional flow model. We first establish that this is computationally hard for a large class of flow models. Motivated by this, we propose a framework for approximate inference that estimates the target conditional as a composition of two flow models. This formulation leads to a stable variational inference training procedure that avoids adversarial training. Our method is evaluated on a variety of inverse problems and is shown to produce high-quality samples with uncertainty quantification. We further demonstrate that our approach can be amortized for zero-shot inference.

BibTeX
@InProceedings{pmlr-v139-whang21b,
  title = 	 {Composing Normalizing Flows for Inverse Problems},
  author =       {Whang, Jay and Lindgren, Erik and Dimakis, Alex},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {11158--11169},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/whang21b/whang21b.pdf},
  url = 	 {https://proceedings.mlr.press/v139/whang21b.html},
  abstract = 	 {Given an inverse problem with a normalizing flow prior, we wish to estimate the distribution of the underlying signal conditioned on the observations. We approach this problem as a task of conditional inference on the pre-trained unconditional flow model. We first establish that this is computationally hard for a large class of flow models. Motivated by this, we propose a framework for approximate inference that estimates the target conditional as a composition of two flow models. This formulation leads to a stable variational inference training procedure that avoids adversarial training. Our method is evaluated on a variety of inverse problems and is shown to produce high-quality samples with uncertainty quantification. We further demonstrate that our approach can be amortized for zero-shot inference.}
}
Composing Normalizing Flows for Inverse Problems · ICML 2021