Second order stochastic gradient update for Cholesky factor in Gaussian variational approximation from Stein's Lemma

10/19/2022
by   Linda S. L. Tan, et al.
0

In stochastic variational inference, use of the reparametrization trick for the multivariate Gaussian gives rise to efficient updates for the mean and Cholesky factor of the covariance matrix, which depend on the first order derivative of the log joint model density. In this article, we show that an alternative unbiased gradient estimate for the Cholesky factor which depends on the second order derivative of the log joint model density can be derived using Stein's Lemma. This leads to a second order stochastic gradient update for the Cholesky factor which is able to improve convergence, as it has variance lower than the first order update (almost negligible) when close to the mode. We also derive second order update for the Cholesky factor of the precision matrix, which is useful when the precision matrix has a sparse structure reflecting conditional independence in the true posterior distribution. Our results can be used to obtain second order natural gradient updates for the Cholesky factor as well, which are more robust compared to updates based on Euclidean gradients.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/01/2021

Explicit natural gradient updates for Cholesky factor in Gaussian variational approximation

Stochastic gradient methods have enabled variational inference for high-...
research
05/18/2016

Gaussian variational approximation with sparse precision matrices

We consider the problem of learning a Gaussian variational approximation...
research
01/24/2018

Gaussian variational approximation for high-dimensional state space models

Our article considers variational approximations of the posterior distri...
research
02/21/2021

Bi-factor and second-order copula models for item response data

Bi-factor and second-order models based on copulas are proposed for item...
research
09/09/2015

Fast Second-Order Stochastic Backpropagation for Variational Inference

We propose a second-order (Hessian or Hessian-free) based optimization m...
research
10/18/2019

Robust modal regression with direct log-density derivative estimation

Modal regression is aimed at estimating the global mode (i.e., global ma...
research
09/27/2018

On some variance reduction properties of the reparameterization trick

The so-called reparameterization trick is widely used in variational inf...

Please sign up or login with your details

Forgot password? Click here to reset