Commutativity and Disentanglement from the Manifold Perspective

10/14/2022
by   Frank Qiu, et al.
0

In this paper, we interpret disentanglement from the manifold perspective and trace how it naturally leads to a necessary and sufficient condition for disentanglement: the disentangled factors must commute with each other. Along the way, we show how some technical results have consequences for the compression and disentanglement of generative models, and we also discuss the practical and theoretical implications of commutativity. Finally, we conclude with a discussion of related approaches to disentanglement and how they relate to our view of disentanglement from the manifold perspective.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/07/2019

On Need for Topology Awareness of Generative Models

Manifold assumption in learning states that: the data lie approximately ...
research
05/27/2019

Universality Theorems for Generative Models

Despite the fact that generative models are extremely successful in prac...
research
12/23/2021

A Point-free Perspective on Lax extensions and Predicate liftings

In this paper we have a fresh look at the connection between lax extensi...
research
12/18/2020

Flow-based Generative Models for Learning Manifold to Manifold Mappings

Many measurements or observations in computer vision and machine learnin...
research
11/15/2020

Functorial Manifold Learning and Overlapping Clustering

We adapt previous research on topological unsupervised learning to devel...
research
02/26/2020

Max-Affine Spline Insights into Deep Generative Networks

We connect a large class of Generative Deep Networks (GDNs) with spline ...
research
12/28/2020

A Technological Perspective on Net Neutrality

This paper serves as a brief technical examination of Net Neutrality and...

Please sign up or login with your details

Forgot password? Click here to reset