Research map / Learning theory and algorithms / Submodular and game algorithms
Learning Tree Structured Potential 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 |
|---|---|---|---|
| Model observations as local optima (potential game) instead of global optima (structured prediction) (ablation) | Tree-structured potential game learner · Synthetic 6-node chain | tree structure recovery | Helped |
| Model observations as local optima instead of global optima (ablation) | Tree-structured potential game learner · Supreme Court 2013 rulings | qualitative agreement with known ideology | Helped |
| Use approximate neighborhood search with Hamming radius h=1 | Dual decomposition learner · Congressional Votes (30 senators) | recovery of party-consistent structure | Helped |
| Restrict local neighborhoods to Hamming distance h=1 instead of exhaustive enumeration | Dual decomposition learner · Complexity | per-run complexity: O(n2 * MaxIter) | Helped |
Closest papers by meaning
- Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints (ICML 2022 · similarity 0.87)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.86)
- Efficient Learning in Polyhedral Games via Best-Response Oracles (AAAI 2024 · similarity 0.85)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.85)
- Learning to Steer Learners in Games (ICML 2025 · similarity 0.85)
- No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics (NeurIPS 2026 · similarity 0.85)
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.
