Research map / Optimization / Nonconvex and smooth optimization
Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical Study
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Stackelberg learning dynamics (implicit, leader accounts for follower best response) instead of simultaneous gradient descent | covariance learning Wasserstein GAN (zero-sum) · Learning covariance matrix, m=2,5,10 | distance from equilibrium ||Sigma - VV^T||_2 and ||W + W^T||_2 convergence speed | Helped |
| Stackelberg learning dynamics instead of simultaneous gradient descent | GAN training, circle configuration (non-saturating objective, ReLU) · Learning mixture of Gaussians (circle) | training stability / convergence to ground-truth distribution | Helped |
| Stackelberg learning dynamics instead of simultaneous gradient descent | GAN training, diamond configuration (saturating objective, Tanh) · Learning mixture of Gaussians (diamond) | generator/discriminator quality at end of training | No clear effect |
| Stackelberg learning dynamics instead of simultaneous gradient descent | MNIST DCGAN · MNIST GAN, mean Inception score over 10 seeds | Inception score | Helped |
Closest papers by meaning
- Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games (NeurIPS 2021 · similarity 0.91)
- A mean-field analysis of two-player zero-sum games (NeurIPS 2020 · similarity 0.90)
- Coordinating Followers to Reach Better Equilibria: End-to-End Gradient Descent for Stackelberg Games (AAAI 2022 · similarity 0.90)
- Towards convergence to Nash equilibria in two-team zero-sum games (ICLR 2023 · similarity 0.90)
- On Last-Iterate Convergence Beyond Zero-Sum Games (ICML 2022 · similarity 0.89)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.