Importance Weighted Autoencoders

by   Yuri Burda, et al.

The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong assumptions about posterior inference, for instance that the posterior distribution is approximately factorial, and that its parameters can be approximated with nonlinear regression from the observations. As we show empirically, the VAE objective can lead to overly simplified representations which fail to use the network's entire modeling capacity. We present the importance weighted autoencoder (IWAE), a generative model with the same architecture as the VAE, but which uses a strictly tighter log-likelihood lower bound derived from importance weighting. In the IWAE, the recognition network uses multiple samples to approximate the posterior, giving it increased flexibility to model complex posteriors which do not fit the VAE modeling assumptions. We show empirically that IWAEs learn richer latent space representations than VAEs, leading to improved test log-likelihood on density estimation benchmarks.


page 1

page 2

page 3

page 4


Tutorial: Deriving the Standard Variational Autoencoder (VAE) Loss Function

In Bayesian machine learning, the posterior distribution is typically co...

Self-Reflective Variational Autoencoder

The Variational Autoencoder (VAE) is a powerful framework for learning p...

MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders

Variational Autoencoder (VAE), a simple and effective deep generative mo...

Importance Weighted Adversarial Variational Autoencoders for Spike Inference from Calcium Imaging Data

The Importance Weighted Auto Encoder (IWAE) objective has been shown to ...

Tree Variational Autoencoders

We propose a new generative hierarchical clustering model that learns a ...

Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach

Variational autoencoder (VAE) is a very successful generative model whos...

Amortized Inference Regularization

The variational autoencoder (VAE) is a popular model for density estimat...

Code Repositories


Generative Models with TensorFlow

view repo


This is a review paper to compare four approaches to solve the problem of intractable posterior.

view repo

Please sign up or login with your details

Forgot password? Click here to reset