Preprint · 2017 · Open access

Convolutional Normalizing Flows

Zheng, Guoqing, Yiming Yang, Jaime Carbonell

arXiv (Cornell University) · Published 7 November 2017 · DOI 10.48550/arxiv.1711.02255

Open PDFView at the publisherCite this paper

In brief

“Convolutional Normalizing Flows” is a 2017 preprint by Zheng, Guoqing and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 15 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
15
Most cited in
2021 (3)
References
18
Authors
3

Abstract

Bayesian posterior inference is prevalent in various machine learning problems. Variational inference provides one way to approximate the posterior distribution, however its expressive power is limited and so is the accuracy of resulting approximation. Recently, there has a trend of using neural networks to approximate the variational posterior distribution due to the flexibility of neural network architecture. One way to construct flexible variational distribution is to warp a simple density into a complex by normalizing flows, where the resulting density can be analytically evaluated. However, there is a trade-off between the flexibility of normalizing flow and computation cost for efficient transformation. In this paper, we propose a simple yet effective architecture of normalizing flows, ConvFlow, based on convolution over the dimensions of random input vector. Experiments on synthetic and real world posterior inference problems demonstrate the effectiveness and efficiency of the proposed method.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Guoqing, Z., Yang, Y., & Carbonell, J. (2017). Convolutional Normalizing Flows. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1711.02255

MLA 9

Guoqing, Zheng,, et al. “Convolutional Normalizing Flows.” arXiv (Cornell University), 2017. https://doi.org/10.48550/arxiv.1711.02255.

Chicago

Guoqing, Zheng,, Yiming Yang, and Jaime Carbonell. 2017. “Convolutional Normalizing Flows.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1711.02255.

Harvard

Guoqing, Z., Yang, Y. and Carbonell, J. (2017) ‘Convolutional Normalizing Flows’, arXiv (Cornell University). doi:10.48550/arxiv.1711.02255.

IEEE

Z. Guoqing, Y. Yang, and J. Carbonell, “Convolutional Normalizing Flows,” arXiv (Cornell University), 2017, doi: 10.48550/arxiv.1711.02255.

BibTeX

@misc{guoqing2017convolutional,
  title     = {{Convolutional Normalizing Flows}},
  author    = {Guoqing, Zheng, and Yang, Yiming and Carbonell, Jaime},
  howpublished = {arXiv (Cornell University)},
  year      = {2017},
  doi       = {10.48550/arxiv.1711.02255},
  url       = {https://doi.org/10.48550/arxiv.1711.02255}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201922
202022
202133
202222
202322
202433
202611

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference

  • normalizing flows
  • variational inference
  • Bayesian posterior inference
  • density estimation
  • computational efficiency

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Guoqing, Z., Yang, Y., & Carbonell, J. (2017). Convolutional Normalizing Flows. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1711.02255

How many times has this paper been cited?

15 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Zheng, Guoqing, Yiming Yang, Jaime Carbonell.

What is the DOI of this paper?

10.48550/arxiv.1711.02255, permanently at https://doi.org/10.48550/arxiv.1711.02255. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.