Research map / Optimization / Optimizers
Coordinating Followers to Reach Better Equilibria: End-to-End Gradient Descent for Stackelberg Games
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 |
|---|---|---|---|
| Use end-to-end gradient descent through sampled follower equilibria instead of black-box optimization or equilibrium reformulation | Multi-follower Stackelberg games · Normal-form games | leader utility | Helped |
| Use end-to-end gradient descent through sampled follower equilibria instead of black-box optimization or equilibrium reformulation | Multi-follower Stackelberg games · Stackelberg security games | leader utility | Helped |
| Use end-to-end gradient descent through sampled follower equilibria instead of black-box optimization or equilibrium reformulation | Multi-follower Stackelberg games · Cyber insurance games | leader utility | Helped |
| Handle equilibrium-dependent constraints with an augmented Lagrangian method | Gradient-based Stackelberg optimization · Normal-form games, Stackelberg security games, and cyber insurance games | constraint violation | Helped |
| Assume optimistic or pessimistic equilibrium selection rather than model the stochastic equilibrium distribution | Stackelberg games with stochastic follower equilibria · Theoretical game in Theorem | leader expected payoff: 0 vs. 2/3 C - ε | Hurt |
Closest papers by meaning
- Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis (NeurIPS 2025 · similarity 0.91)
- Competitive Gradient Descent (NeurIPS 2019 · similarity 0.91)
- Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games (NeurIPS 2021 · similarity 0.91)
- Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical Study (ICML 2020 · similarity 0.90)
- Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization (ICLR 2024 · similarity 0.88)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.88)
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.