Methods › General › Large Batch Optimization › LAMB

LAMB

199 papers tagged archive 2025-07-28

Introduced by Yang You et al. in Large Batch Optimization for Deep Learning: Training BERT in 76 minutes

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

LAMB is a a layerwise adaptive large batch optimization technique. It provides a strategy for adapting the learning rate in large batch settings. LAMB uses Adam as the base algorithm and then forms an update as:

rₜ = mₜ/(√(vₜ) + ϵ) xₜ₊₁⁽ⁱ⁾ = xₜ⁽ⁱ⁾ - ηₜ(ϕ(|| xₜ⁽ⁱ⁾ ||))/(|| mₜ⁽ⁱ⁾ ||)(rₜ⁽ⁱ⁾+λxₜ⁽ⁱ⁾)

Unlike LARS, the adaptivity of LAMB is two-fold: (i) per dimension normalization with respect to the square root of the second moment used in Adam and (ii) layerwise normalization obtained due to layerwise adaptivity.

PaperSourceSee Code · cybertronai/pytorch-lamb

In Syntology repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: listed only). The lookup matched a paper by its title, the paper Syntology's graph keys as 2025.acl-short.96, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about the paper Syntology's graph keys as 2025.acl-short.96) is about this method is not checked.

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: 199 · with a code link: 86 · where Syntology ran a sample: 21 (15 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 (21 of 199 tagged: 15 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 199, 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 194 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 Modelling30
Language Modeling25
Sentence23
Question Answering15
Sentiment Analysis14
Text Classification14
text-classification13
Transfer Learning11
Named Entity Recognition (NER)10
NER9
Named Entity Recognition9
Natural Language Understanding9
named-entity-recognition9
Image Classification8
Data Augmentation7
General Classification7
Reading Comprehension7
GPU6
Machine Reading Comprehension6
Natural Language Inference6

Usage over time archive 2025-07-28

Papers per year tagged with LAMB: 2012 to 2025, peak 67 67 0 2012: 1 paper 2012 2013: 0 papers 2013 2014: 1 paper 2014 2015: 0 papers 2015 2016: 0 papers 2016 2017: 0 papers 2017 2018: 1 paper 2018 2019: 5 papers 2019 2020: 50 papers 2020 2021: 67 papers 2021 2022: 31 papers 2022 2023: 18 papers 2023 2024: 18 papers 2024 2025: 7 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (199 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

Large Batch 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