Importance Weighted Autoencoders

09/01/2015
by   Yuri Burda, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/21/2019

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

In Bayesian machine learning, the posterior distribution is typically co...
research
07/10/2020

Self-Reflective Variational Autoencoder

The Variational Autoencoder (VAE) is a powerful framework for learning p...
research
01/06/2019

MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders

Variational Autoencoder (VAE), a simple and effective deep generative mo...
research
06/07/2019

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

The Importance Weighted Auto Encoder (IWAE) objective has been shown to ...
research
06/15/2023

Tree Variational Autoencoders

We propose a new generative hierarchical clustering model that learns a ...
research
02/05/2021

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

Variational autoencoder (VAE) is a very successful generative model whos...
research
05/23/2018

Amortized Inference Regularization

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

Please sign up or login with your details

Forgot password? Click here to reset