Improving Sampling from Generative Autoencoders with Markov Chains

10/28/2016
by   Antonia Creswell, et al.
0

We focus on generative autoencoders, such as variational or adversarial autoencoders, which jointly learn a generative model alongside an inference model. Generative autoencoders are those which are trained to softly enforce a prior on the latent distribution learned by the inference model. We call the distribution to which the inference model maps observed samples, the learned latent distribution, which may not be consistent with the prior. We formulate a Markov chain Monte Carlo (MCMC) sampling process, equivalent to iteratively decoding and encoding, which allows us to sample from the learned latent distribution. Since, the generative model learns to map from the learned latent distribution, rather than the prior, we may use MCMC to improve the quality of samples drawn from the generative model, especially when the learned latent distribution is far from the prior. Using MCMC sampling, we are able to reveal previously unseen differences between generative autoencoders trained either with or without a denoising criterion.

READ FULL TEXT

page 3

page 5

page 10

page 14

page 15

page 16

page 17

research
04/26/2019

Flow-based generative models for Markov chain Monte Carlo in lattice field theory

A Markov chain update scheme using a machine-learned flow-based generati...
research
05/20/2018

Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding

Variational Autoencoders (VAEs) are a popular generative model, but one ...
research
06/02/2023

Generative Autoencoders as Watermark Attackers: Analyses of Vulnerabilities and Threats

Invisible watermarks safeguard images' copyrights by embedding hidden me...
research
02/03/2022

MRI Reconstruction via Data Driven Markov Chain with Joint Uncertainty Estimation

We introduce a framework that enables efficient sampling from learned pr...
research
10/01/2020

VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models

Energy-based models (EBMs) have recently been successful in representing...
research
03/20/2017

Learning to Generate Samples from Noise through Infusion Training

In this work, we investigate a novel training procedure to learn a gener...
research
09/21/2022

Approximate sampling and estimation of partition functions using neural networks

We consider the closely related problems of sampling from a distribution...

Please sign up or login with your details

Forgot password? Click here to reset