Learning low bending and low distortion manifold embeddings

by   Juliane Braunsmann, et al.

Autoencoders are a widespread tool in machine learning to transform high-dimensional data into a lowerdimensional representation which still exhibits the essential characteristics of the input. The encoder provides an embedding from the input data manifold into a latent space which may then be used for further processing. For instance, learning interpolation on the manifold may be simplified via the new manifold representation in latent space. The efficiency of such further processing heavily depends on the regularity and structure of the embedding. In this article, the embedding into latent space is regularized via a loss function that promotes an as isometric and as flat embedding as possible. The required training data comprises pairs of nearby points on the input manifold together with their local distance and their local Frechet average. This regularity loss functional even allows to train the encoder on its own. The loss functional is computed via a Monte Carlo integration which is shown to be consistent with a geometric loss functional defined directly on the embedding map. Numerical tests are performed using image data that encodes different data manifolds. The results show that smooth manifold embeddings in latent space are obtained. These embeddings are regular enough such that interpolation between not too distant points on the manifold is well approximated by linear interpolation in latent space.


page 9

page 10

page 12

page 14


Learning Low Bending and Low Distortion Manifold Embeddings: Theory and Applications

Autoencoders, which consist of an encoder and a decoder, are widely used...

Deep Clustering and Representation Learning that Preserves Geometric Structures

In this paper, we propose a novel framework for Deep Clustering and Repr...

Atlas Generative Models and Geodesic Interpolation

Generative neural networks have a well recognized ability to estimate un...

A Geometric Perspective on Autoencoders

This paper presents the geometric aspect of the autoencoder framework, w...

Agent Embeddings: A Latent Representation for Pole-Balancing Networks

We show that it is possible to reduce a high-dimensional object like a n...

Conditional generation of multi-modal data using constrained embedding space mapping

We present a conditional generative model that maps low-dimensional embe...

Uniform Interpolation Constrained Geodesic Learning on Data Manifold

In this paper, we propose a method to learn a minimizing geodesic within...

Please sign up or login with your details

Forgot password? Click here to reset