Methods › General › Stochastic Optimization › Forward gradient
Forward gradient
Introduced by Atılım Güneş Baydin et al. in Gradients without Backpropagation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Forward gradients are unbiased estimators of the gradient ∇f(θ) for a function f: ℝⁿ →ℝ, given by g(θ) = ⟨∇f(θ) , v ⟩v.
Here v = (v₁, …, vₙ) is a random vector, which must satisfy the following conditions in order for g(θ) to be an unbiased estimator of ∇f(θ)
- vᵢ ⊥vⱼ for all i ≠j
- 𝔼[vᵢ] = 0 for all i
- 𝕍[vᵢ] = 1 for all i
Forward gradients can be computed with a single jvp (Jacobian Vector Product), which enables the use of the forward mode of autodifferentiation instead of the usual reverse mode, which has worse computational characteristics.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: Split Forward Gradient (Split-FG); Forward-DP; gradient EM; Forward DEER; Forward Flow; Fast Forward; Gradient Cuff; Forward Replay.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 12 · with a code link: 8 · where Syntology ran a sample: 4 (4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 12 tagged: 4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 12 of 12, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
A Scalable Hybrid Training Approach for Recurrent Spiking Neural Networks 17 Jun 2025 · 1 repository · arXiv:2506.14464
-
Flexible and Efficient Surrogate Gradient Modeling with Forward Gradient Injection 31 May 2024 · 0 repositories · arXiv:2406.00177
-
Projected Forward Gradient-Guided Frank-Wolfe Algorithm via Variance Reduction 19 Mar 2024 · 0 repositories · arXiv:2403.12511
-
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark 18 Feb 2024 · 1 repository · arXiv:2402.11592Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update 1 Feb 2024 · 1 repository · arXiv:2402.00348Syntology official (archive's flag): 8 ran · 8 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 8 pointer-only (licence)
-
Convergence guarantees for forward gradient descent in the linear regression model 26 Sep 2023 · 0 repositories · arXiv:2309.15001
-
Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism 21 Sep 2023 · 0 repositories
-
Can Forward Gradient Match Backpropagation? 12 Jun 2023 · 1 repository · arXiv:2306.06968
-
Low-Variance Forward Gradients using Direct Feedback Alignment and Momentum 14 Dec 2022 · 1 repository · arXiv:2212.07282
-
Scaling Forward Gradient With Local Losses 7 Oct 2022 · 1 repository · arXiv:2210.03310
-
Optimization without Backpropagation 13 Sep 2022 · 1 repository · arXiv:2209.06302Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples)
-
Gradients without Backpropagation 17 Feb 2022 · 3 repositories · arXiv:2202.08587Syntology 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
7 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Benchmarking | 1 |
| Imitation Learning | 1 |
| Memorization | 1 |
| Model Optimization | 1 |
| Offline RL | 1 |
| Reinforcement Learning (RL) | 1 |
| regression | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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