Normalizing Flows: An Introduction and Review of Current Methods.

@article{Kobyzev2020NormalizingFA,
  title={Normalizing Flows: An Introduction and Review of Current Methods.},
  author={I. Kobyzev and Simon Prince and Marcus A. Brubaker},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  year={2020}
}
Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution learning. We aim to provide context and explanation of the models, review current state-of-the-art literature, and identify open questions and promising future directions. 
90 Citations
Flow-based Autoregressive Structured Prediction of Human Motion
  • Highly Influenced
  • PDF
Robust normalizing flows using Bernstein-type polynomials
  • Highly Influenced
  • PDF
Bidirectional Modeling and Analysis of Brain Aging with Normalizing Flows
  • Highly Influenced
  • PDF
Weighting-Based Treatment Effect Estimation via Distribution Learning
  • Highly Influenced
  • PDF
Automatic Backward Filtering Forward Guiding for Markov processes and graphical models
  • 1
  • Highly Influenced
  • PDF
Manifold Density Estimation via Generalized Dequantization
  • PDF
A Neural Network MCMC Sampler That Maximizes Proposal Entropy
  • 1
  • PDF
Causal Autoregressive Flows
  • 1
  • PDF
Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstruction
  • 2
  • PDF
D'ya like DAGs? A Survey on Structure Learning and Causal Discovery
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 94 REFERENCES
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
  • 116
  • Highly Influential
  • PDF
Glow: Generative Flow with Invertible 1x1 Convolutions
  • 918
  • Highly Influential
  • PDF
Neural Ordinary Differential Equations
  • 938
  • Highly Influential
  • PDF
Density estimation using Real NVP
  • 1,141
  • Highly Influential
  • PDF
Masked Autoregressive Flow for Density Estimation
  • 438
  • Highly Influential
  • PDF
NICE: Non-linear Independent Components Estimation
  • 780
  • Highly Influential
  • PDF
Variational Inference with Normalizing Flows
  • 1,340
  • Highly Influential
  • PDF
Invertible Residual Networks
  • 193
  • Highly Influential
  • PDF
VideoFlow: A Flow-Based Generative Model for Video
  • 64
  • Highly Influential
Learning across scales - A multiscale method for Convolution Neural Networks
  • 45
  • Highly Influential
  • PDF
...
1
2
3
4
5
...