Variance reduction properties of the reparameterization trick

09/27/2018
by   Ming Xu, et al.
0

The reparameterization trick is widely used in variational inference as it yields more accurate estimates of the gradient of the variational objective than alternative approaches such as the score function method. Although there is overwhelming empirical evidence in the literature showing its success, there is relatively little research exploring why the reparameterization trick is so effective. We explore this under the idealized assumptions that the variational approximation is a mean-field Gaussian density and that the log of the joint density of the model parameters and the data is a quadratic function that depends on the variational mean. From this, we show that the marginal variances of the reparameterization gradient estimator are smaller than those of the score function gradient estimator. We apply the result of our idealized analysis to real-world examples.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/27/2018

On some variance reduction properties of the reparameterization trick

The so-called reparameterization trick is widely used in variational inf...
research
10/20/2020

VarGrad: A Low-Variance Gradient Estimator for Variational Inference

We analyse the properties of an unbiased gradient estimator of the ELBO ...
research
07/29/2020

Approximation Based Variance Reduction for Reparameterization Gradients

Flexible variational distributions improve variational inference but are...
research
01/26/2021

Generalized Doubly Reparameterized Gradient Estimators

Efficient low-variance gradient estimation enabled by the reparameteriza...
research
10/19/2022

Rethinking Sharpness-Aware Minimization as Variational Inference

Sharpness-aware minimization (SAM) aims to improve the generalisation of...
research
12/24/2020

Variational Determinant Estimation with Spherical Normalizing Flows

This paper introduces the Variational Determinant Estimator (VDE), a var...
research
11/19/2017

A note on quadratic approximations of logistic log-likelihoods

Quadratic approximations of logistic log-likelihoods are fundamental to ...

Please sign up or login with your details

Forgot password? Click here to reset