Methods › General › Stochastic Optimization › AdaSmooth

Adaptive Smooth Optimizer

AdaSmooth

2 papers tagged archive 2025-07-28

Introduced by Jun Lu in AdaSmooth: An Adaptive Learning Rate Method based on Effective Ratio

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

AdaSmooth is a stochastic optimization technique that allows for per-dimension learning rate method for SGD. It is an extension of Adagrad and AdaDelta that seek to reduce its aggressive, monotonically decreasing learning rate. Instead of accumulating all past squared gradients, Adadelta restricts the window of accumulated past gradients to a fixed size w while AdaSmooth adaptively selects the size of the window.

Given the window size M, the effective ratio is calculated by

eₜ = sₜ/nₜ= (| xₜ - x_(t-M)|)/(∑ᵢ₌₀ᴹ⁻¹ | xₜ₋ᵢ - xₜ₋₁₋ᵢ|) = (| ∑ᵢ₌₀ᴹ⁻¹ Δxₜ₋₁₋ᵢ|)/(∑ᵢ₌₀ᴹ⁻¹ | Δxₜ₋₁₋ᵢ|).

Given the effective ratio, the scaled smoothing constant is obtained by:

cₜ = ( ρ₂- ρ₁) ×eₜ + (1-ρ₂),

The running average E[g²]ₜ at time step t then depends only on the previous average and current gradient:

E[g²]ₜ = cₜ² ⊙gₜ² + (1-cₜ² )⊙E[g²]ₜ₋₁

Usually ρ₁ is set to around $0.5$ and ρ₂ is set to around 0.99. The update step the follows:

Δxₜ = -η/(√(E[g²]ₜ + ϵ)) ⊙gₜ,

which is incorporated into the final update:

xₜ₊₁ = xₜ + Δxₜ.

The main advantage of AdaSmooth is its faster convergence rate and insensitivity to hyperparameters.

PaperSource

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.

Tasks archive 2025-07-28

1 task the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Stochastic Optimization2

Usage over time archive 2025-07-28

Papers per year tagged with AdaSmooth: 2022 to 2022, peak 2 2 0 2022: 2 papers 2022
Papers per year the archive tags with this method, by the paper's archive date (2 dated). Bars are counts, not a trend claim.

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

Stochastic Optimization

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