Methods › General › Optimization › Lion

Evolved Sign Momentum

Lion

32 papers tagged archive 2025-07-28

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

The Lion optimizer is discovered by symbolic program search. It is more memory-efficient than most adaptive optimizers as it only needs to momentum. The update of Lion is produced by the sign function.

See Code · google/automl

Papers archive 2025-07-28

30 shown of 32, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 38 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 Modeling4
Language Modelling4
Quantization3
Contrastive Learning2
GPU2
Position2
Stochastic Optimization2
parameter-efficient fine-tuning2
3D Object Detection1
Attribute1
Audio-Visual Speech Recognition1
Diversity1
Federated Learning1
Handwritten Text Recognition1
Image Classification1
L2 Regularization1
LAMBADA1
Large Language Model1
Lip Reading1
Lipreading1

Usage over time archive 2025-07-28

Papers per year tagged with Lion: 2023 to 2025, peak 14 14 0 2023: 12 papers 2023 2024: 14 papers 2024 2025: 6 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (32 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

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