DeepAI AI Chat
Log In Sign Up

Identifying latent distances with Finslerian geometry

by   Alison Pouplin, et al.
University of Cambridge
RISE Research Institutes of Sweden

Riemannian geometry provides powerful tools to explore the latent space of generative models while preserving the inherent structure of the data manifold. Lengths, energies and volume measures can be derived from a pullback metric, defined through the immersion that maps the latent space to the data space. With this in mind, most generative models are stochastic, and so is the pullback metric. Manipulating stochastic objects is strenuous in practice. In order to perform operations such as interpolations, or measuring the distance between data points, we need a deterministic approximation of the pullback metric. In this work, we are defining a new metric as the expected length derived from the stochastic pullback metric. We show this metric is Finslerian, and we compare it with the expected pullback metric. In high dimensions, we show that the metrics converge to each other at a rate of 𝒪(1/D).


page 8

page 9

page 10

page 11

page 15

page 16


A prior-based approximate latent Riemannian metric

Stochastic generative models enable us to capture the geometric structur...

Expected path length on random manifolds

Manifold learning seeks a low dimensional representation that faithfully...

Geometrically Enriched Latent Spaces

A common assumption in generative models is that the generator immerses ...

Learning Flat Latent Manifolds with VAEs

Measuring the similarity between data points often requires domain knowl...

LIMP: Learning Latent Shape Representations with Metric Preservation Priors

In this paper, we advocate the adoption of metric preservation as a powe...

Pulling back information geometry

Latent space geometry has shown itself to provide a rich and rigorous fr...

Geometry-Aware Hamiltonian Variational Auto-Encoder

Variational auto-encoders (VAEs) have proven to be a well suited tool fo...