Methods › General › Stochastic Optimization › SGD

Stochastic Gradient Descent

SGD

introduced 1951 2,021 papers tagged archive 2025-07-28

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

Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using all available data. That is for weights w and a loss function L we have:

wₜ₊₁ = wₜ - η∇̂_wL(wₜ)

Where η is a learning rate. SGD reduces redundancy compared to batch gradient descent - which recomputes gradients for similar examples before each parameter update - so it is usually much faster.

(Image Source: here)

See Code · pytorch/pytorch

Papers archive 2025-07-28

30 shown of 2,021, 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 362 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
Stochastic Optimization149
Image Classification122
Federated Learning110
image-classification102
BIG-bench Machine Learning66
Deep Learning66
regression59
Quantization55
Language Modelling52
GPU49
Generalization Bounds45
Language Modeling44
Distributed Optimization39
General Classification39
Computational Efficiency27
Data Augmentation27
Second-order methods25
Privacy Preserving24
Learning Theory23
Speech Recognition23

Usage over time archive 2025-07-28

Papers per year tagged with SGD: 2011 to 2025, peak 337 337 0 2011: 3 papers 2011 2012: 2 papers 2013: 10 papers 2013 2014: 10 papers 2015: 25 papers 2015 2016: 41 papers 2017: 75 papers 2017 2018: 152 papers 2019: 218 papers 2019 2020: 291 papers 2021: 337 papers 2021 2022: 226 papers 2023: 270 papers 2023 2024: 244 papers 2025: 116 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (2,020 dated, 1 undated not charted). 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

Stochastic 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