ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables

05/28/2021
by   Alek Dimitriev, et al.
0

Estimating the gradients for binary variables is a task that arises frequently in various domains, such as training discrete latent variable models. What has been commonly used is a REINFORCE based Monte Carlo estimation method that uses either independent samples or pairs of negatively correlated samples. To better utilize more than two samples, we propose ARMS, an Antithetic REINFORCE-based Multi-Sample gradient estimator. ARMS uses a copula to generate any number of mutually antithetic samples. It is unbiased, has low variance, and generalizes both DisARM, which we show to be ARMS with two samples, and the leave-one-out REINFORCE (LOORF) estimator, which is ARMS with uncorrelated samples. We evaluate ARMS on several datasets for training generative models, and our experimental results show that it outperforms competing methods. We also develop a version of ARMS for optimizing the multi-sample variational bound, and show that it outperforms both VIMCO and DisARM. The code is publicly available.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2021

CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator

Accurately backpropagating the gradient through categorical variables is...
research
04/23/2014

Most Correlated Arms Identification

We study the problem of finding the most mutually correlated arms among ...
research
02/22/2016

Variational inference for Monte Carlo objectives

Recent progress in deep latent variable models has largely been driven b...
research
02/25/2019

Censored Regression for Modelling International Small Arms Trading and its "Forensic" Use for Exploring Unreported Trades

In this paper we use a censored regression model to analyse data on the ...
research
07/30/2018

ARM: Augment-REINFORCE-Merge Gradient for Discrete Latent Variable Models

To backpropagate the gradients through discrete stochastic layers, we en...
research
09/07/2023

DBsurf: A Discrepancy Based Method for Discrete Stochastic Gradient Estimation

Computing gradients of an expectation with respect to the distributional...
research
03/08/2018

Exploring Dependence Structures in the International Arms Trade Network

In the paper we analyse dependence structures among international trade ...

Please sign up or login with your details

Forgot password? Click here to reset