Methods › General › Stochastic Optimization › AdaBound

AdaBound

11 papers tagged archive 2025-07-28

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

AdaBound is a variant of the Adam stochastic optimizer which is designed to be more robust to extreme learning rates. Dynamic bounds are employed on learning rates, where the lower and upper bound are initialized as zero and infinity respectively, and they both smoothly converge to a constant final step size. AdaBound can be regarded as an adaptive method at the beginning of training, and thereafter it gradually and smoothly transforms to SGD (or with momentum) as the time step increases.

gₜ = ∇fₜ(xₜ)

mₜ = β₁ₜmₜ₋₁ + (1-β₁ₜ)gₜ

vₜ = β₂vₜ₋₁ + (1-β₂)gₜ² and Vₜ = diag(vₜ)

η̂ₜ = Clip(α/√(Vₜ), ηₗ(t), ηᵤ(t)) and ηₜ = η̂ₜ/√(t)

xₜ₊₁ = Π_(ℱ, diag(ηₜ⁻¹))(xₜ - ηₜ ⊙mₜ )

Where α is the initial step size, and ηₗ and ηᵤ are the lower and upper bound functions respectively.

Source: Adaptive Gradient Methods with Dynamic Bound of Learning RateSee Code · Luolc/AdaBound

Papers archive 2025-07-28

11 shown of 11, 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

15 tasks 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 Optimization3
regression2
Benchmarking1
Bilevel Optimization1
Clustering1
General Classification1
Image Classification1
Machine Translation1
Management1
Natural Language Understanding1
Text Categorization1
Text Classification1
Translation1
Vocal Bursts Type Prediction1
text-classification1

Usage over time archive 2025-07-28

Papers per year tagged with AdaBound: 2019 to 2023, peak 4 4 0 2019: 4 papers 2019 2020: 4 papers 2020 2021: 2 papers 2021 2022: 0 papers 2022 2023: 1 paper 2023
Papers per year the archive tags with this method, by the paper's archive date (11 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