Pith. sign in

REVIEW 1 cited by

Optimization without Backpropagation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2209.06302 v1 pith:DJV3HIVY submitted 2022-09-13 cs.LG math.OC

Gabriel Belouze This is my paper · ORCID
classification cs.LGmath.OC
keywords gradientsforwardbackpropagationoptimizationapproximatingautodifferentiationbeenbest
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Forward gradients have been recently introduced to bypass backpropagation in autodifferentiation, while retaining unbiased estimators of true gradients. We derive an optimality condition to obtain best approximating forward gradients, which leads us to mathematical insights that suggest optimization in high dimension is challenging with forward gradients. Our extensive experiments on test functions support this claim.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients

    cs.LG 2025-09 conditional novelty 6.0 of 10

    A warm-up phase of ordinary federated training followed by zeroth-order forward-pass-only updates lets low-resource clients participate in federated pre-training from random initialization.

Pith tools