Unbiased Implicit Variational Inference

by   Michalis K. Titsias, et al.

We develop unbiased implicit variational inference (UIVI), a method that expands the applicability of variational inference by defining an expressive variational family. UIVI considers an implicit variational distribution obtained in a hierarchical manner using a simple reparameterizable distribution whose variational parameters are defined by arbitrarily flexible deep neural networks. Unlike previous works, UIVI directly optimizes the evidence lower bound (ELBO) rather than an approximation to the ELBO. We demonstrate UIVI on several models, including Bayesian multinomial logistic regression and variational autoencoders, and show that UIVI achieves both tighter ELBO and better predictive performance than existing approaches at a similar computational cost.


page 1

page 2

page 3

page 4


Doubly Semi-Implicit Variational Inference

We extend the existing framework of semi-implicit variational inference ...

Hierarchical Implicit Models and Likelihood-Free Variational Inference

Implicit probabilistic models are a flexible class of models defined by ...

Variational Orthogonal Features

Sparse stochastic variational inference allows Gaussian process models t...

Implicit Weight Uncertainty in Neural Networks

We interpret HyperNetworks within the framework of variational inference...

Design of Communication Systems using Deep Learning: A Variational Inference Perspective

An approach to design end to end communication system using deep learnin...

Nonparametric variational inference

Variational methods are widely used for approximate posterior inference....

A Spectral Approach to Gradient Estimation for Implicit Distributions

Recently there have been increasing interests in learning and inference ...

Please sign up or login with your details

Forgot password? Click here to reset