Papers › REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

21 Mar 2017NeurIPS 2017 12arXiv:1703.07370archive 2025-07-28

George Tucker, andriy mnih, Chris J. Maddison, Dieterich Lawson, Jascha Sohl-Dickstein

Learning in models with discrete latent variables is challenging due to high variance gradient estimators. Generally, approaches have relied on control variates to reduce the variance of the REINFORCE estimator. Recent work (Jang et al. 2016, Maddison et al. 2016) has taken a different approach, introducing a continuous relaxation of discrete variables to produce low-variance, but biased, gradient estimates. In this work, we combine the two approaches through a novel control variate that produces low-variance, \emph{unbiased} gradient estimates. Then, we introduce a modification to the continuous relaxation and show that the tightness of the relaxation can be adapted online, removing it as a hyperparameter. We show state-of-the-art variance reduction on several benchmark generative modeling tasks, generally leading to faster convergence to a better final log-likelihood.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tensorflow/models officialmentioned in papertf report
TalkToTheGAN/REGAN mentioned on GitHubpytorch report
tensorflow/models mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

REINFORCE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections