Pith. sign in

REVIEW

Straight-Through Estimator as Projected Wasserstein Gradient Flow

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1910.02176 v1 pith:WZ32YUIP submitted 2019-10-05 cs.LG stat.ML

classification cs.LGstat.ML
keywords estimatordiscretegradientvariablesdistributionsflowpoissonprojected
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The Straight-Through (ST) estimator is a widely used technique for back-propagating gradients through discrete random variables. However, this effective method lacks theoretical justification. In this paper, we show that ST can be interpreted as the simulation of the projected Wasserstein gradient flow (pWGF). Based on this understanding, a theoretical foundation is established to justify the convergence properties of ST. Further, another pWGF estimator variant is proposed, which exhibits superior performance on distributions with infinite support,e.g., Poisson distributions. Empirically, we show that ST and our proposed estimator, while applied to different types of discrete structures (including both Bernoulli and Poisson latent variables), exhibit comparable or even better performances relative to other state-of-the-art methods. Our results uncover the origin of the widespread adoption of the ST estimator and represent a helpful step towards exploring alternative gradient estimators for discrete variables.

Discussion (0). Continue with ORCID to comment.

Pith tools