Density estimation on low-dimensional manifolds: an inflation-deflation approach

05/25/2021
by   Christian Horvat, et al.
0

Normalizing Flows (NFs) are universal density estimators based on Neuronal Networks. However, this universality is limited: the density's support needs to be diffeomorphic to a Euclidean space. In this paper, we propose a novel method to overcome this limitation without sacrificing universality. The proposed method inflates the data manifold by adding noise in the normal space, trains an NF on this inflated manifold, and, finally, deflates the learned density. Our main result provides sufficient conditions on the manifold and the specific choice of noise under which the corresponding estimator is exact. Our method has the same computational complexity as NFs and does not require computing an inverse flow. We also show that, if the embedding dimension is much larger than the manifold dimension, noise in the normal space can be well approximated by Gaussian noise. This allows to use our method for approximating arbitrary densities on non-flat manifolds provided that the manifold dimension is known.

READ FULL TEXT

Authors

page 15

page 22

06/09/2021

Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows

Normalizing flows are generative models that provide tractable density e...
02/14/2021

Manifold Density Estimation via Generalized Dequantization

Density estimation is an important technique for characterizing distribu...
06/18/2020

Neural Manifold Ordinary Differential Equations

To better conform to data geometry, recent deep generative modelling tec...
04/16/2022

Detection of Small Holes by the Scale-Invariant Robust Density-Aware Distance (RDAD) Filtration

A novel topological-data-analytical (TDA) method is proposed to distingu...
09/17/2020

LAAT: Locally Aligned Ant Technique for detecting manifolds of varying density

Dimensionality reduction and clustering are often used as preliminary st...
04/27/2021

Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution

Neuroevolution is an alternative to gradient-based optimisation that has...
07/16/2003

Manifold Learning with Geodesic Minimal Spanning Trees

In the manifold learning problem one seeks to discover a smooth low dime...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.