mlsanityData to 7 Oct 2026

InvertibleNetworks.jl: A Julia package for scalable normalizing flows

arXiv 2312.13480 ↗First posted 20 Dec 2023cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

InvertibleNetworks.jl is a Julia package designed for the scalable implementation of normalizing flows, a method for density estimation and sampling in high-dimensional distributions. This package excels in memory efficiency by leveraging the inherent invertibility of normalizing flows, which significantly reduces memory requirements during backpropagation compared to existing normalizing flow packages that rely on automatic differentiation frameworks. InvertibleNetworks.jl has been adapted for diverse applications, including seismic imaging, medical imaging, and CO2 monitoring, demonstrating its effectiveness in learning high-dimensional distributions.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 21 of its 36 references that are in the map. First posted on arXiv 20 Dec 2023.

Builds on

21 of 36 references.

References · 21

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  4. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  5. 2023Self-Consuming Generative Models Go MADcited by 239
  6. 2020BayesFlow: Learning complex stochastic models with invertible neural networkscited by 139
  7. 2019A Differentiable Programming System to Bridge Machine Learning and Scientific Computingcited by 81
  8. 2023normflows: A PyTorch Package for Normalizing Flowscited by 56
  9. 2019HINT: Hierarchical Invertible Neural Transport for Density Estimation and Bayesian Inferencecited by 31
  10. 2022Reliable amortized variational inference with physics-based latent distribution correctioncited by 25
  11. 2021Preconditioned training of normalizing flows for variational inference in inverse problemscited by 19
  12. 2019Fully Hyperbolic Convolutional Neural Networkscited by 15
9 more
  1. 2022Conditional Injective Flows for Bayesian Imagingcited by 13
  2. 2020Parameterizing uncertainty by deep invertible networks, an application to reservoir characterizationcited by 11
  3. 2023Solving multiphysics-based inverse problems with learned surrogates and constraintscited by 9
  4. 2023Amortized Normalizing Flows for Transcranial Ultrasound with Uncertainty Quantificationcited by 8
  5. 2023Learned multiphysics inversion with differentiable programming and machine learningcited by 7
  6. 2023Inference of CO2 flow patterns -- a feasibility studycited by 4
  7. 2022Memory Efficient Invertible Neural Networks for 3D Photoacoustic Imagingcited by 3
  8. 2023Refining Amortized Posterior Approximations using Gradient-Based Summary Statisticscited by 3
  9. 2019Symmetric block-low-rank layers for fully reversible multilevel neural networkscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024ASPIRE: Iterative Amortized Posterior Inference for Bayesian Inverse Problemscited by 11
  2. 2024Probabilistic Bayesian optimal experimental design using conditional normalizing flowscited by 10
  3. 2024An uncertainty-aware Digital Shadow for underground multimodal CO2 storage monitoringcited by 5
  4. 2025Advancing Geological Carbon Storage Monitoring With 3d Digital Shadow Technologycited by 1
  5. 2024Fully invertible hyperbolic neural networks for segmenting large-scale surface and sub-surface datacited by 0
  6. 2025Enhancing Robustness Of Digital Shadow For CO2 Storage Monitoring With Augmented Rock Physics Modelingcited by 0