Nonlinear Isometric Manifold Learning for Injective Normalizing Flows

03/08/2022
by   Eike Cramer, et al.
0

To model manifold data using normalizing flows, we propose to employ the isometric autoencoder to design nonlinear encodings with explicit inverses. The isometry allows us to separate manifold learning and density estimation and train both parts to high accuracy. Applied to the MNIST data set, the combined approach generates high-quality images.

READ FULL TEXT

Authors

page 6

06/07/2022

Joint Manifold Learning and Density Estimation Using Normalizing Flows

Based on the manifold hypothesis, real-world data often lie on a low-dim...
03/31/2020

Flows for simultaneous manifold learning and density estimation

We introduce manifold-modeling flows (MFMFs), a new class of generative ...
02/14/2022

Principal Manifold Flows

Normalizing flows map an independent set of latent variables to their sa...
02/14/2021

Manifold Density Estimation via Generalized Dequantization

Density estimation is an important technique for characterizing distribu...
11/20/2020

ScalarFlow: A Large-Scale Volumetric Data Set of Real-world Scalar Transport Flows for Computer Animation and Machine Learning

In this paper, we present ScalarFlow, a first large-scale data set of re...
06/02/2021

Rectangular Flows for Manifold Learning

Normalizing flows are invertible neural networks with tractable change-o...
07/27/2020

Normal-bundle Bootstrap

Probabilistic models of data sets often exhibit salient geometric struct...
This week in AI

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