Fast Approximate Geodesics for Deep Generative Models

by   Nutan Chen, et al.

The length of the geodesic between two data points along the Riemannian manifold, induced by a deep generative model, yields a principled measure of similarity. Applications have so far been limited to low-dimensional latent spaces, as the method is computationally demanding: it constitutes to solving a non-convex optimisation problem. Our approach is to tackle a relaxation: finding shortest paths in a finite graph of samples from the aggregate approximate posterior can be solved exactly, at greatly reduced runtime, and without notable loss in quality. The method is hence applicable to high-dimensional problems in the visual domain. We validate the approach empirically on a series of experiments using variational autoencoders applied to image data, tackling the Chair, Faces and FashionMNIST data sets.


page 4

page 5

page 6

page 9


Metrics for Deep Generative Models

Neural samplers such as variational autoencoders (VAEs) or generative ad...

Geodesic Clustering in Deep Generative Models

Deep generative models are tremendously successful in learning low-dimen...

Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining

Many important problems in science and engineering, such as drug design,...

Stochastic Backpropagation and Approximate Inference in Deep Generative Models

We marry ideas from deep neural networks and approximate Bayesian infere...

The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders

Training and using modern neural-network based latent-variable generativ...

Deep Generative Endmember Modeling: An Application to Unsupervised Spectral Unmixing

Endmember (EM) spectral variability can greatly impact the performance o...

Amortized Global Search for Efficient Preliminary Trajectory Design with Deep Generative Models

Preliminary trajectory design is a global search problem that seeks mult...

Please sign up or login with your details

Forgot password? Click here to reset