Methods › General › Learning Rate Schedules › Inverse Square Root Schedule

Inverse Square Root Schedule

702 papers tagged archive 2025-07-28

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

Inverse Square Root is a learning rate schedule 1 / √(max(n, k)) where n is the current training iteration and k is the number of warm-up steps. This sets a constant learning rate for the first k steps, then exponentially decays the learning rate until pre-training is over.

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: Banded Inverse Square Root (BISR); Square Root Loss (SRL); Square Root Correction; Square Root Bundle Adjustment; square-root entropy scheduling; Square Root Curvature Transform; Mean Root Square Normalization (MRSNorm); Root Mean Square Layer Normalization (RMSNorm).

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: 702 · with a code link: 349 · where Syntology ran a sample: 97 (83 with a run with no instrument failure, 14 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (97 of 702 tagged: 83 with a run with no instrument failure, 14 where every run was a failure of Syntology's instrument)

Page 1 of 8: papers 1 to 100 of 702, 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 467 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 Modelling123
Language Modeling96
Question Answering84
Decoder78
Text Generation65
Sentence55
Translation45
Retrieval40
Transfer Learning40
Machine Translation39
Natural Language Understanding29
Semantic Parsing23
Abstractive Text Summarization22
Sentiment Analysis22
Natural Language Inference20
Code Generation19
Data Augmentation19
Diversity18
Text Summarization18
Knowledge Graphs17

Usage over time archive 2025-07-28

Papers per year tagged with Inverse Square Root Schedule: 2015 to 2025, peak 197 197 0 2015: 1 paper 2015 2016: 0 papers 2016 2017: 0 papers 2017 2018: 0 papers 2018 2019: 2 papers 2019 2020: 30 papers 2020 2021: 108 papers 2021 2022: 163 papers 2022 2023: 197 papers 2023 2024: 151 papers 2024 2025: 50 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (702 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

Learning Rate Schedules

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