Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows

Abstract

We introduce Projected Latent Markov Chain Monte Carlo (PL-MCMC), a technique for sampling from the exact conditional distributions learned by normalizing flows. As a conditional sampling method, PL-MCMC enables Monte Carlo Expectation Maximization (MC-EM) training of normalizing flows from incomplete data. Through experimental tests applying normalizing flows to missing data tasks for a variety of data sets, we demonstrate the efficacy of PL-MCMC for conditional sampling from normalizing flows.

Cite

Text

Cannella et al. "Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows." International Conference on Learning Representations, 2021.

Markdown

[Cannella et al. "Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows." International Conference on Learning Representations, 2021.](https://mlanthology.org/iclr/2021/cannella2021iclr-projected/)

BibTeX

@inproceedings{cannella2021iclr-projected,
  title     = {{Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows}},
  author    = {Cannella, Chris and Soltani, Mohammadreza and Tarokh, Vahid},
  booktitle = {International Conference on Learning Representations},
  year      = {2021},
  url       = {https://mlanthology.org/iclr/2021/cannella2021iclr-projected/}
}