Methods › General › Learning Rate Schedules › Step Decay

Step Decay

73 papers tagged archive 2025-07-28

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

Step Decay is a learning rate schedule that drops the learning rate by a factor every few epochs, where the number of epochs is a hyperparameter.

Image Credit: Suki Lau

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: Decay RNN; pruning mask decay; Low-Rank Decay (LRD); sparse structure decay; Temporal-Decay Shapley; Space-sampled Value Decay; Sample Weight Decay (SWD); decay-aware neural network.

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: 73 · with a code link: 68 · where Syntology ran a sample: 41 (33 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (41 of 73 tagged: 33 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 73 of 73, 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 84 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
Object Detection39
Image Classification38
object-detection23
General Classification17
Object16
image-classification15
Semantic Segmentation11
Classification8
Object Recognition6
Real-Time Object Detection6
Instance Segmentation5
Domain Generalization4
Neural Architecture Search4
Data Augmentation3
GPU3
Medical Image Classification3
Person Re-Identification3
Segmentation3
Stochastic Optimization3
Decoder2

Usage over time archive 2025-07-28

Papers per year tagged with Step Decay: 2012 to 2025, peak 27 27 0 2012: 1 paper 2012 2013: 2 papers 2013 2014: 3 papers 2014 2015: 3 papers 2015 2016: 9 papers 2016 2017: 6 papers 2017 2018: 11 papers 2018 2019: 27 papers 2019 2020: 3 papers 2020 2021: 3 papers 2021 2022: 1 paper 2022 2023: 2 papers 2023 2024: 1 paper 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (73 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