Skip to content
Source

Literature Review

Theory

Gaussianization

The original Gaussianization algorithms.

  • Gaussianization - Chen & Gopinath - (2000) - PDF
  • Nonlinear Extraction of 'Independent Components' of elliptically symmetric densities using radial Gaussianization - Lyu & Simoncelli - Technical Report (2008) - PDF

Applications

  • Gaussianization for fast and accurate inference from cosmological data - Schuhman et. al. - (2016) - PDF
  • Estimating Information in Earth Data Cubes - Johnson et. al. - EGU 2018
  • Multivariate Gaussianization in Earth and Climate Sciences - Johnson et. al. - Climate Informatics 2019 - repo
  • Climate Model Intercomparison with Multivariate Information Theoretic Measures - Johnson et. al. - AGU 2019 - slides
  • Information theory measures and RBIG for Spatial-Temporal Data analysis - Johnson et. al. - In progress

Things to Think about

  • A Note on the Evaluation of Generative Models - Theis et. al. - ICLR 2016 - PDF

Journal Articles

  • Iterative Gaussianization: from ICA to Random Rotations - Laparra et. al. (2011) - IEEE Transactions on Neural Networks

RBIG

The most updated Gaussianization algorithm which generalizes the original algorithms. It is more computationally efficient and still very simple to implement.

  • Iterative Gaussianization: from ICA to Random Rotations - Laparra et. al. - IEEE TNNs - Paper

Applications


Generalized Divisive Normalization

This can be thought of as an approximation to the Gaussianization

  • Density Modeling of Images Using a Generalized Normalized Transformation - Balle et al. - ICLR (2016) - arxiv | Lecture | PyTorch | TensorFlow
  • End-to-end Optimized Image Compression - Balle et. al. - CVPR (2017) - axriv
  • Learning Divisive Normalization in Primary Visual Cortex - Gunthner et. al. - bioarxiv