Stochastic Backpropagation and Approximate Inference in Deep Generative Models

TL;DR

This paper introduces a scalable deep generative model framework combining neural networks with approximate Bayesian inference, utilizing stochastic back-propagation for joint training of generative and recognition models.

Contribution

It presents a novel algorithm that integrates recognition models with stochastic back-propagation for efficient inference and learning in deep generative models.

Findings

Generates realistic samples from complex data

Accurately imputes missing data

Effective for high-dimensional data visualization

Abstract

We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a recognition model to represent approximate posterior distributions, and that acts as a stochastic encoder of the data. We develop stochastic back-propagation -- rules for back-propagation through stochastic variables -- and use this to develop an algorithm that allows for joint optimisation of the parameters of both the generative and recognition model. We demonstrate on several real-world data sets that the model generates realistic samples, provides accurate imputations of missing data and is a useful tool for high-dimensional data visualisation.