Methods › General › Large Batch Optimization › Nesterov Accelerated Gradient

Nesterov Accelerated Gradient

introduced 1983 34 papers tagged archive 2025-07-28

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

Nesterov Accelerated Gradient is a momentum-based SGD optimizer that "looks ahead" to where the parameters will be to calculate the gradient ex post rather than ex ante:

vₜ = γvₜ₋₁ - η∇_θJ(θₜ₋₁+γvₜ₋₁) θₜ = θₜ₋₁ + vₜ γ, η∈ℝ^+

Like SGD with momentum γ is usually set to $0.9$. η and γ are usually less than $1$.

The intuition is that the standard momentum method first computes the gradient at the current location and then takes a big jump in the direction of the updated accumulated gradient. In contrast Nesterov momentum first makes a big jump in the direction of the previous accumulated gradient and then measures the gradient where it ends up and makes a correction. The idea being that it is better to correct a mistake after you have made it.

Image Source: Geoff Hinton lecture notes

Papers archive 2025-07-28

30 shown of 34, 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 59 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
Image Classification8
Stochastic Optimization5
image-classification4
General Classification3
Object Recognition3
Denoising2
Language Modelling2
Semantic Segmentation2
2D Human Pose Estimation1
Adversarial Attack1
All1
Bilevel Optimization1
Breast Tumour Classification1
CT Reconstruction1
Classification1
Computational Efficiency1
Crowd Counting1
Decoder1
Diagnostic1
Distributed Computing1

Usage over time archive 2025-07-28

Papers per year tagged with Nesterov Accelerated Gradient: 2016 to 2025, peak 6 6 0 2016: 4 papers 2016 2017: 0 papers 2017 2018: 4 papers 2018 2019: 6 papers 2019 2020: 6 papers 2020 2021: 3 papers 2021 2022: 2 papers 2022 2023: 1 paper 2023 2024: 6 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (34 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