Gaussianization Flows

by   Chenlin Meng, et al.

Iterative Gaussianization is a fixed-point iteration procedure that can transform any continuous random vector into a Gaussian one. Based on iterative Gaussianization, we propose a new type of normalizing flow model that enables both efficient computation of likelihoods and efficient inversion for sample generation. We demonstrate that these models, named Gaussianization flows, are universal approximators for continuous probability distributions under some regularity conditions. Because of this guaranteed expressivity, they can capture multimodal target distributions without compromising the efficiency of sample generation. Experimentally, we show that Gaussianization flows achieve better or comparable performance on several tabular datasets compared to other efficiently invertible flow models such as Real NVP, Glow and FFJORD. In particular, Gaussianization flows are easier to initialize, demonstrate better robustness with respect to different transformations of the training data, and generalize better on small training sets.


page 6

page 14


Sinusoidal Flow: A Fast Invertible Autoregressive Flow

Normalising flows offer a flexible way of modelling continuous probabili...

Neural Autoregressive Flows

Normalizing flows and autoregressive models have been successfully combi...

Equivariant flow matching

Normalizing flows are a class of deep generative models that are especia...

Graphical Normalizing Flows

Normalizing flows model complex probability distributions by combining a...

Supervised Neural Networks for Illiquid Alternative Asset Cash Flow Forecasting

Institutional investors have been increasing the allocation of the illiq...

Equivariant Normalizing Flows for Point Processes and Sets

A point process describes how random sets of exchangeable points are gen...

Self Normalizing Flows

Efficient gradient computation of the Jacobian determinant term is a cor...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset