ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2008.01998
19
6

Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds

5 August 2020
Valentin Liévin
Andrea Dittadi
Anders Christensen
Ole Winther
    DRL
ArXivPDFHTML
Abstract

This paper introduces novel results for the score function gradient estimator of the importance weighted variational bound (IWAE). We prove that in the limit of large KKK (number of importance samples) one can choose the control variate such that the Signal-to-Noise ratio (SNR) of the estimator grows as K\sqrt{K}K​. This is in contrast to the standard pathwise gradient estimator where the SNR decreases as 1/K1/\sqrt{K}1/K​. Based on our theoretical findings we develop a novel control variate that extends on VIMCO. Empirically, for the training of both continuous and discrete generative models, the proposed method yields superior variance reduction, resulting in an SNR for IWAE that increases with KKK without relying on the reparameterization trick. The novel estimator is competitive with state-of-the-art reparameterization-free gradient estimators such as Reweighted Wake-Sleep (RWS) and the thermodynamic variational objective (TVO) when training generative models.

View on arXiv
Comments on this paper