Methods › General › Stochastic Optimization › AdamW

AdamW

206 papers tagged archive 2025-07-28

Introduced by Ilya Loshchilov et al. in Decoupled Weight Decay Regularization

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

AdamW is a stochastic optimization method that modifies the typical implementation of weight decay in Adam, by decoupling weight decay from the gradient update. To see this, L₂ regularization in Adam is usually implemented with the below modification where wₜ is the rate of the weight decay at time t:

gₜ = ∇f(θₜ) + wₜθₜ

while AdamW adjusts the weight decay term to appear in the gradient update:

θ_(t+1, i) = θ_(t, i) - η(1/(√(v̂ₜ + ϵ))·m̂ₜ + w_(t, i)θ_(t, i)), ∀t

PaperSourceSee Code · pytorch/pytorch

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: AdamW-GS; DP-AdamW-BC; QEF-GT-AdamW; Stiefel-AdamW; AdamW-influence; AdamW-Adafactor hybrid; Shape-Boundary Orthogonal AdamW (SBO-AdamW).

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: 206 · with a code link: 114 · where Syntology ran a sample: 43 (37 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (43 of 206 tagged: 37 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)

Page 1 of 3: papers 1 to 100 of 206, 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.

Tasks archive 2025-07-28

20 shown of 207 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
Language Modelling24
Language Modeling22
Image Classification17
image-classification17
Decoder12
Question Answering11
Document Classification10
GPU10
Sentence10
Object Detection9
Abstractive Text Summarization8
Classification8
Articles7
Deep Learning7
Text Classification7
Natural Language Inference6
Semantic Segmentation6
object-detection6
Segmentation5
Text Summarization5

Usage over time archive 2025-07-28

Papers per year tagged with AdamW: 2017 to 2025, peak 62 62 0 2017: 1 paper 2017 2018: 1 paper 2018 2019: 2 papers 2019 2020: 10 papers 2020 2021: 24 papers 2021 2022: 30 papers 2022 2023: 62 papers 2023 2024: 47 papers 2024 2025: 29 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (206 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