Research map / Multi-agent systems and games / Games and equilibria
Deep Contract Design via Discontinuous Networks
Tonghan Wang, Paul Duetting, Dmitry Ivanov, Inbal Talgam-Cohen, David C. Parkes
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 DeLU instead of continuous ReLU network | contract design network · Synthetic contract design | optimality: +28.29% | Improved |
| use DeLU instead of picking best training contract | contract design network · Synthetic contract design | optimality: +23.84% | Improved |
| DeLU on large problems with more than 1,000 outcomes | DeLU · Large-scale contract design | optimality vs training data: at least 1.7 times better | Improved |
| use gradient-based inference instead of LP inference (ablation) | DeLU · Synthetic contract design | optimality: -7.56% | Hurt |
| use gradient-based inference instead of LP inference (ablation) | DeLU · Inference time, m=25 | inference time: 50-90% less overhead | Improved |
| initialize gradient inference with random contracts instead of training set (ablation) | DeLU gradient inference · (5,16) problem | optimality: 95.29 -> 95.33 | No clear effect |
| initialize gradient inference with random contracts instead of training set (ablation) | DeLU gradient inference · (32,50) problem | optimality: 88.43 -> 88.46 | No clear effect |
| increase independent cost weight beta_p from 0.0 to 0.9 at alpha_p=0.5 | DeLU · Cost correlation study | optimality: 88.79 -> 97.23 | Improved |
| increase alpha_p from 0.5 to 0.9 at beta_p=0.6 | DeLU · Cost correlation study | optimality: 95.22 -> 91.97 | Hurt |
| add sub-argmax inference to gradient-based inference (ablation) | DeLU · Boundary alignment study | optimality | Mixed |
| higher boundary alignment degree between DeLU and true utility | DeLU LP inference · Boundary alignment study | optimality | Improved |
Closest papers by meaning
- Learning Optimal Contracts: How to Exploit Small Action Spaces (ICLR 2024 · similarity 0.87)
- Contract Design Under Approximate Best Responses (ICML 2025 · similarity 0.87)
- Contracting with a Learning Agent (NeurIPS 2024 · similarity 0.86)
- Paid with Models: Optimal Contract Design for Collaborative Machine Learning (AAAI 2025 · similarity 0.85)
- Worst-Case VCG Redistribution Mechanism Design Based on the Lottery Ticket Hypothesis (AAAI 2024 · similarity 0.82)
- Learning in Online Principal-Agent Interactions: The Power of Menus (AAAI 2024 · similarity 0.82)
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.
