Research map / Learning theory and algorithms / Submodular and game algorithms
Learning in Multi-Stage Decentralized Matching Markets
Xiaowu Dai, Michael Jordan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 multi-stage rather than single-stage decentralized matching | P2 in the four-arm, three-agent example · Four-arm, three-agent matching example | welfare: 0 to 1.5 | Improved |
| Have P1 use LUB-CDM while P2 continues using CDM | P2 · Two-stage matching example | payoff | Hurt |
| Use LUB-CDM instead of the patient strategy | P1 · Search-model simulation | payoff | Improved |
| Target arms with lower acceptance uncertainty in early stages | Agents in multi-stage decentralized matching · Multi-stage decentralized matching | expected payoff | Improved |
| Target arms with higher rather than lower uncertainty of acceptance | Agents in multi-stage decentralized matching · Multi-stage decentralized matching | level of justified envy | Improved |
| Increase the uncertainty regularization parameter η | Agents using the multi-stage strategy · Multi-stage decentralized matching | level of justified envy | Hurt |
Closest papers by meaning
- Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning (NeurIPS 2024 · similarity 0.90)
- Decentralized and Uncoordinated Learning of Stable Matchings: A Game-Theoretic Approach (AAAI 2025 · similarity 0.89)
- Fair and Welfare-Efficient Constrained Multi-Matchings under Uncertainty (NeurIPS 2024 · similarity 0.89)
- Improved Bandits in Many-to-One Matching Markets with Incentive Compatibility (AAAI 2024 · similarity 0.89)
- Competing Bandits in Matching Markets via Super Stability (ICML 2025 · similarity 0.88)
- Stable Matching with Ties: Approximation Ratios and Learning (NeurIPS 2025 · similarity 0.87)
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.
