Methods › General › Stochastic Optimization › Adam

Adam

24,390 papers tagged archive 2025-07-28

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

Adam is an adaptive learning rate optimization algorithm that utilises both momentum and scaling, combining the benefits of RMSProp and SGD w/th Momentum. The optimizer is designed to be appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients.

The weight updates are performed as:

wₜ = wₜ₋₁ - ηm̂ₜ/(√(v̂ₜ) + ϵ)

with

m̂ₜ = mₜ/(1-βᵗ₁)

v̂ₜ = vₜ/(1-βᵗ₂)

mₜ = β₁mₜ₋₁ + (1-β₁)gₜ

vₜ = β₂vₜ₋₁ + (1-β₂)gₜ²

η is the step size/learning rate, around 1e-3 in the original paper. ϵ is a small number, typically 1e-8 or 1e-10, to prevent dividing by zero. β₁ and β₂ are forgetting parameters, with typical values 0.9 and 0.999, respectively.

Source: Adam: A Method for Stochastic OptimizationSee Code · pytorch/pytorch

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 87 in the graph, strongest link: mentioned on GitHub). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:1412.6980) is about this method is not checked.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:1412.6980 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 27 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 4 honoured, 2 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified (of 37 harvested samples) · 8 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

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.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 24,390 · with a code link: 10,944 · where Syntology ran a sample: 3,424 (2,801 with a run with no instrument failure, 623 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (3,424 of 24,390 tagged: 2,801 with a run with no instrument failure, 623 where every run was a failure of Syntology's instrument)

Page 1 of 244: papers 1 to 100 of 24,390, 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 2,551 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 Modelling2,917
Language Modeling2,286
Retrieval1,734
Question Answering1,420
RAG1,290
Sentence1,289
Decoder1,284
Retrieval-augmented Generation1,121
Translation1,009
Machine Translation905
Large Language Model811
Text Generation723
Semantic Segmentation707
Image Classification660
Transfer Learning651
Representation Learning596
Sentiment Analysis595
Object Detection585
Text Classification559
Classification554

Usage over time archive 2025-07-28

Papers per year tagged with Adam: 1986 to 2025, peak 6,749 6,749 0 1986: 1 paper 1986 1987: 0 papers 1988: 0 papers 1989: 0 papers 1990: 0 papers 1991: 0 papers 1991 1992: 0 papers 1993: 0 papers 1994: 0 papers 1995: 0 papers 1996: 0 papers 1996 1997: 0 papers 1998: 0 papers 1999: 0 papers 2000: 0 papers 2001: 0 papers 2001 2002: 0 papers 2003: 0 papers 2004: 0 papers 2005: 0 papers 2006: 0 papers 2006 2007: 0 papers 2008: 0 papers 2009: 0 papers 2010: 0 papers 2011: 0 papers 2011 2012: 0 papers 2013: 0 papers 2014: 1 paper 2015: 6 papers 2016: 23 papers 2016 2017: 70 papers 2018: 222 papers 2019: 1198 papers 2020: 2319 papers 2021: 3153 papers 2021 2022: 3169 papers 2023: 5041 papers 2024: 6749 papers 2025: 2438 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (24,390 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