Variational Autoencoders: A Harmonic Perspective

05/31/2021
by   Alexander Camuto, et al.
0

In this work we study Variational Autoencoders (VAEs) from the perspective of harmonic analysis. By viewing a VAE's latent space as a Gaussian Space, a variety of measure space, we derive a series of results that show that the encoder variance of a VAE controls the frequency content of the functions parameterised by the VAE encoder and decoder neural networks. In particular we demonstrate that larger encoder variances reduce the high frequency content of these functions. Our analysis allows us to show that increasing this variance effectively induces a soft Lipschitz constraint on the decoder network of a VAE, which is a core contributor to the adversarial robustness of VAEs. We further demonstrate that adding Gaussian noise to the input of a VAE allows us to more finely control the frequency content and the Lipschitz constant of the VAE encoder networks. To support our theoretical analysis we run experiments with VAEs with small fully-connected neural networks and with larger convolutional networks, demonstrating empirically that our theory holds for a variety of neural network architectures.

READ FULL TEXT
research
02/15/2021

Certifiably Robust Variational Autoencoders

We introduce an approach for training Variational Autoencoders (VAEs) th...
research
04/20/2020

On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond

Variational autoencoders (VAEs) combine latent variables with amortized ...
research
10/28/2021

Probabilistic Autoencoder using Fisher Information

Neural Networks play a growing role in many science disciplines, includi...
research
12/06/2022

Three Variations on Variational Autoencoders

Variational autoencoders (VAEs) are one class of generative probabilisti...
research
06/18/2020

Neural Architecture Optimization with Graph VAE

Due to their high computational efficiency on a continuous space, gradie...
research
11/25/2018

Sequential Variational Autoencoders for Collaborative Filtering

Variational autoencoders were proven successful in domains such as compu...
research
03/14/2019

Diagnosing and Enhancing VAE Models

Although variational autoencoders (VAEs) represent a widely influential ...

Please sign up or login with your details

Forgot password? Click here to reset