Joint Manifold Learning and Density Estimation Using Normalizing Flows

by   Seyedeh Fatemeh Razavi, et al.

Based on the manifold hypothesis, real-world data often lie on a low-dimensional manifold, while normalizing flows as a likelihood-based generative model are incapable of finding this manifold due to their structural constraints. So, one interesting question arises: "Can we find sub-manifold(s) of data in normalizing flows and estimate the density of the data on the sub-manifold(s)?". In this paper, we introduce two approaches, namely per-pixel penalized log-likelihood and hierarchical training, to answer the mentioned question. We propose a single-step method for joint manifold learning and density estimation by disentangling the transformed space obtained by normalizing flows to manifold and off-manifold parts. This is done by a per-pixel penalized likelihood function for learning a sub-manifold of the data. Normalizing flows assume the transformed data is Gaussianizationed, but this imposed assumption is not necessarily true, especially in high dimensions. To tackle this problem, a hierarchical training approach is employed to improve the density estimation on the sub-manifold. The results validate the superiority of the proposed methods in simultaneous manifold learning and density estimation using normalizing flows in terms of generated image quality and likelihood.


page 10

page 11

page 13

page 14

page 18

page 19

page 21

page 22


Flows for simultaneous manifold learning and density estimation

We introduce manifold-modeling flows (MFMFs), a new class of generative ...

Nonlinear Isometric Manifold Learning for Injective Normalizing Flows

To model manifold data using normalizing flows, we propose to employ the...

Normalizing Flows Across Dimensions

Real-world data with underlying structure, such as pictures of faces, ar...

Diagnosing and Fixing Manifold Overfitting in Deep Generative Models

Likelihood-based, or explicit, deep generative models use neural network...

Rectangular Flows for Manifold Learning

Normalizing flows are invertible neural networks with tractable change-o...

Environmental Economics and Uncertainty: Review and a Machine Learning Outlook

Economic assessment in environmental science concerns the measurement or...

Score Matching for Truncated Density Estimation on a Manifold

When observations are truncated, we are limited to an incomplete picture...