Papers › Can Forward Gradient Match Backpropagation?

Can Forward Gradient Match Backpropagation?

12 Jun 2023arXiv:2306.06968archive 2025-07-28

Louis Fournier, Stéphane Rivaud, Eugene Belilovsky, Michael Eickenberg, Edouard Oyallon

Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding problems generally associated with backpropagation gradient computation, such as locking and memorization requirements. The cost is the requirement to guess the step direction, which is hard in high dimensions. While current solutions rely on weighted averages over isotropic guess vector distributions, we propose to strongly bias our gradient guesses in directions that are much more promising, such as feedback obtained from small, local auxiliary networks. For a standard computer vision neural network, we conduct a rigorous study systematically covering a variety of combinations of gradient targets and gradient guesses, including those previously presented in the literature. We find that using gradients obtained from a local loss as a candidate direction drastically improves on random noise in Forward Gradient methods.

PaperPDFCode

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

Code

streethagore/forwardlocalgradient officialmentioned in paperpytorch 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.

Tasks

Memorization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Forward gradient

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