Generalized Transformation-based Gradient

11/06/2019
by   Anbang Wu, et al.
0

The reparameterization trick has become one of the most useful tools in the field of variational inference. However, the reparameterization trick is based on the standardization transformation which restricts the scope of application of this method to distributions that have tractable inverse cumulative distribution functions or are expressible as deterministic transformations of such distributions. In this paper, we generalized the reparameterization trick by allowing a general transformation. We discover that the proposed model is a special case of control variate indicating that the proposed model can combine the advantages of CV and generalized reparameterization. Based on the proposed gradient model, we propose a new polynomial-based gradient estimator which has better theoretical performance than the reparameterization trick under certain condition and can be applied to a larger class of variational distributions. In studies of synthetic and real data, we show that our proposed gradient estimator has a significantly lower gradient variance than other state-of-the-art methods thus enabling a faster inference procedure.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/18/2016

Reparameterization Gradients through Acceptance-Rejection Sampling Algorithms

Variational inference using the reparameterization trick has enabled lar...
research
10/07/2016

The Generalized Reparameterization Gradient

The reparameterization gradient has become a widely used method to obtai...
research
07/29/2020

Approximation Based Variance Reduction for Reparameterization Gradients

Flexible variational distributions improve variational inference but are...
research
11/17/2021

Power Generalized DUS Transformation of Exponential Distribution

DUS transformation of lifetime distributions received attention by engin...
research
08/15/2023

Natural Evolution Strategies as a Black Box Estimator for Stochastic Variational Inference

Stochastic variational inference and its derivatives in the form of vari...
research
06/07/2018

A Spectral Approach to Gradient Estimation for Implicit Distributions

Recently there have been increasing interests in learning and inference ...
research
06/02/2021

A Differentiable Point Process with Its Application to Spiking Neural Networks

This paper is concerned about a learning algorithm for a probabilistic m...

Please sign up or login with your details

Forgot password? Click here to reset