Methods › General › Optimization › TTUR

Two Time-scale Update Rule

TTUR

133 papers tagged archive 2025-07-28

Introduced by Martin Heusel et al. in GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

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

The Two Time-scale Update Rule (TTUR) is an update rule for generative adversarial networks trained with stochastic gradient descent. TTUR has an individual learning rate for both the discriminator and the generator. The main premise is that the discriminator converges to a local minimum when the generator is fixed. If the generator changes slowly enough, then the discriminator still converges, since the generator perturbations are small. Besides ensuring convergence, the performance may also improve since the discriminator must first learn new patterns before they are transferred to the generator. In contrast, a generator which is overly fast, drives the discriminator steadily into new regions without capturing its gathered information.

PaperSourceSee Code · yccyenchicheng/pytorch-WGAN-GP-TTUR-CelebA

Papers archive 2025-07-28

30 shown of 133, 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 142 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 Generation37
Conditional Image Generation14
Generative Adversarial Network10
reinforcement-learning9
Multi-agent Reinforcement Learning7
Reinforcement Learning7
Data Augmentation6
Reinforcement Learning (RL)6
Super-Resolution6
Decision Making5
Unconditional Image Generation5
Vocal Bursts Intensity Prediction5
Attribute4
Clustering4
Denoising4
Diversity4
Object4
Transfer Learning4
Benchmarking3
Decoder3

Usage over time archive 2025-07-28

Papers per year tagged with TTUR: 2017 to 2024, peak 37 37 0 2017: 1 paper 2017 2018: 2 papers 2018 2019: 9 papers 2019 2020: 28 papers 2020 2021: 20 papers 2021 2022: 34 papers 2022 2023: 37 papers 2023 2024: 2 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (133 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

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