Methods › General › Stochastic Optimization › AdaMax

AdaMax

9 papers tagged archive 2025-07-28

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

AdaMax is a generalisation of Adam from the l₂ norm to the l_∞ norm. Define:

uₜ = β^∞₂vₜ₋₁ + (1-β^∞₂)|gₜ|^∞

= max(β₂·vₜ₋₁, |gₜ|)

We can plug into the Adam update equation by replacing √(v̂ₜ + ϵ) with uₜ to obtain the AdaMax update rule:

θₜ₊₁ = θₜ - η/uₜm̂ₜ

Common default values are η= 0.002 and β₁=0.9 and β₂=0.999.

Source: Adam: A Method for Stochastic OptimizationSee Code · pytorch/pytorch

Papers archive 2025-07-28

9 shown of 9, 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

13 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
Deep Learning2
Image Generation2
Transfer Learning2
Cancer Classification1
Image Classification1
Intrusion Detection1
Quantization1
Speech Recognition1
Stochastic Optimization1
Time Series1
Time Series Analysis1
image-classification1
speech-recognition1

Usage over time archive 2025-07-28

Papers per year tagged with AdaMax: 2014 to 2024, peak 3 3 0 2014: 1 paper 2014 2015: 0 papers 2015 2016: 0 papers 2016 2017: 0 papers 2017 2018: 0 papers 2018 2019: 0 papers 2019 2020: 1 paper 2020 2021: 0 papers 2021 2022: 2 papers 2022 2023: 3 papers 2023 2024: 2 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (9 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

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