The Riemannian Geometry of Deep Generative Models

Abstract

Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space. Under certain regularity conditions, these models parameterize nonlinear manifolds in the data space. In this paper, we investigate the Riemannian geometry of these generated manifolds. First, we develop efficient algorithms for computing geodesic curves, which provide an intrinsic notion of distance between points on the manifold. Second, we develop an algorithm for parallel translation of a tangent vector along a path on the manifold. We show how parallel translation can be used to generate analogies, i.e., to transport a change in one data point into a semantically similar change of another data point. Our experiments on real image data show that the manifolds learned by deep generative models, while nonlinear, are surprisingly close to zero curvature. The practical implication is that linear paths in the latent space closely approximate geodesics on the generated manifold. However, further investigation into this phenomenon is warranted, to identify if there are other architectures or datasets where curvature plays a more prominent role. We believe that exploring the Riemannian geometry of deep generative models, using the tools developed in this paper, will be an important step in understanding the high-dimensional, nonlinear spaces these models learn.

arXiv comment9 pages

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Towards Deeper Understanding of Variational Autoencoding Models
• Deep Learning Face Attributes in the Wild

Cited by in corpus (11)

• Deep generative models in inversion: a review and development of a new approach based on a variational autoencoder
• Gradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?
• Geometry Score: A Method For Comparing Generative Adversarial Networks
• The Deep Kernelized Autoencoder
• Latent Space Non-Linear Statistics
• Investigating Cosmological GAN Emulators Using Latent Space Interpolation
• Only Bayes should learn a manifold (on the estimation of differential geometric structure from data)
• Manifold regularization with GANs for semi-supervised learning
• Latent Space Cartography: Generalised Metric-Inspired Measures and Measure-Based Transformations for Generative Models
• Learning Manifold Implicitly via Explicit Heat-Kernel Learning
• Encoder-Powered Generative Adversarial Networks