</> Code with Papers by Syntology

Methods › General › Large Batch Optimization › AdaGrad

AdaGrad

introduced 2011 191 papers tagged archive 2025-07-28

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

AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring features, and larger updates for parameters associated with infrequently occurring features. In its update rule, Adagrad modifies the general learning rate η at each time step t for every parameter θᵢ based on the past gradients for θᵢ:

θ_(t+1, i) = θ_(t, i) - η/(√(G_(t, ii) + ϵ))g_(t, i)

The benefit of AdaGrad is that it eliminates the need to manually tune the learning rate; most leave it at a default value of $0.01$. Its main weakness is the accumulation of the squared gradients in the denominator. Since every added term is positive, the accumulated sum keeps growing during training, causing the learning rate to shrink and becoming infinitesimally small.

Image: Alec Radford

See Code · Dawn-Of-Eve/nadir

Papers archive 2025-07-28

30 shown of 191, 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 118 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 Optimization26
Language Modelling14
Language Modeling13
BIG-bench Machine Learning7
Image Classification7
Representation Learning7
Second-order methods7
Computational Efficiency6
image-classification6
Text Generation5
Translation4
Deep Learning3
Distributed Optimization3
Federated Learning3
GPU3
Link Prediction3
Machine Translation3
Multi-Task Learning3
Prediction3
Self-Supervised Learning3

Usage over time archive 2025-07-28

Papers per year tagged with AdaGrad: 2013 to 2025, peak 30 30 0 2013: 1 paper 2013 2014: 0 papers 2014 2015: 4 papers 2015 2016: 4 papers 2016 2017: 8 papers 2017 2018: 12 papers 2018 2019: 20 papers 2019 2020: 22 papers 2020 2021: 29 papers 2021 2022: 30 papers 2022 2023: 25 papers 2023 2024: 28 papers 2024 2025: 8 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (191 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

Large Batch OptimizationStochastic 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