Methods › General › Learning Rate Schedules › Cosine Power Annealing

Cosine Power Annealing

6 papers tagged archive 2025-07-28

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

Interpolation between exponential decay and cosine annealing.

Source: sharpDARTS: Faster and More Accurate Differentiable...See Code · raw.githubusercontent.com/ahundt/sharpDARTS/master/cnn/cosine_power_annealing.py

Papers archive 2025-07-28

6 shown of 6, 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

11 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
Neural Architecture Search5
Image Classification4
image-classification3
AutoML2
Face Recognition2
Reinforcement Learning2
GPU1
Hyperparameter Optimization1
Reinforcement Learning (RL)1
Stochastic Optimization1
reinforcement-learning1

Usage over time archive 2025-07-28

Papers per year tagged with Cosine Power Annealing: 2019 to 2022, peak 4 4 0 2019: 4 papers 2019 2020: 1 paper 2020 2021: 0 papers 2021 2022: 1 paper 2022
Papers per year the archive tags with this method, by the paper's archive date (6 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