Methods › General › Stochastic Optimization › AggMo
AggMo
Introduced by James Lucas et al. in Aggregated Momentum: Stability Through Passive Damping
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Aggregated Momentum (AggMo) is a variant of the classical momentum stochastic optimizer which maintains several velocity vectors with different β parameters. AggMo averages the velocity vectors when updating the parameters. It resolves the problem of choosing a momentum parameter by taking a linear combination of multiple momentum buffers. Each of K momentum buffers have a different discount factor β∈ℝᴷ, and these are averaged for the update. The update rule is:
vₜ⁽ⁱ⁾ = β⁽ⁱ⁾vₜ₋₁⁽ⁱ⁾ - ∇_θf(θₜ₋₁)
θₜ = θₜ₋₁ + γₜ/K∑ᴷᵢ₌₁vₜ⁽ⁱ⁾
where v⁽ⁱ⁾₀ for each i. The vector β = [β⁽¹⁾, …, β⁽ᴷ⁾] is the dampening factor.
Papers archive 2025-07-28
1 shown of 1, 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.
-
Aggregated Momentum: Stability Through Passive Damping 1 Apr 2018 · 1 repository · arXiv:1804.00325
Tasks archive 2025-07-28
The archive attaches no task to a paper tagged with this method.
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