Methods › General › Stochastic Optimization › QHM
QHM
Introduced by Jerry Ma et al. in Quasi-hyperbolic momentum and Adam for deep learning
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Quasi-Hyperbolic Momentum (QHM) is a stochastic optimization technique that alters momentum SGD with a momentum step, averaging an SGD step with a momentum step:
gₜ₊₁ = βgₜ + (1-β)·∇L̂ₜ(θₜ) θₜ₊₁ = θₜ - α[(1-v)·∇L̂ₜ(θₜ) + v·gₜ₊₁]
The authors suggest a rule of thumb of v = 0.7 and β= 0.999.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Understanding the Role of Momentum in Stochastic Gradient Methods 30 Oct 2019 · 1 repository · arXiv:1910.13962
-
Quasi-hyperbolic momentum and Adam for deep learning 16 Oct 2018 · 2 repositories · arXiv:1810.06801Syntology ran 0 of 7 samples · 7 unverified · 7 pointer-only (licence)
Tasks archive 2025-07-28
2 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 |
|---|---|
| Stochastic Optimization | 2 |
| Deep Learning | 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