Research map / Federated learning and privacy / Differential privacy
Bounded-Loss Private Prediction Markets
Rafael Frongillo, Bo Waggoner
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 |
|---|---|---|---|
| Add a transaction fee equal to α to the private market | Private prediction market · Private prediction market | designer budget: unbounded loss -> B_1/λ | Improved |
| Replace a fixed-horizon market with adaptively growing stages funded by completed-stage fees | Transaction-fee private market · Adaptive private prediction market | designer budget: superconstant in T -> bounded | Improved |
| Keep the transaction fee fixed at α across adaptive stages | Adaptive market · Adaptive private prediction market | incentive to trade: 2α-incentive to trade | Improved |
| Allocate stage precision and failure probabilities as convergent sequences | Adaptive market · Adaptive private prediction market | accuracy: (α,γ/2), (α/2,γ/4), ... -> (α,γ) | Improved |
Closest papers by meaning
- Learning-augmented private algorithms for multiple quantile release (ICML 2023 · similarity 0.87)
- Private Online Prediction from Experts with Small Losses (NeurIPS 2026 · similarity 0.86)
- Incentives in Private Collaborative Machine Learning (NeurIPS 2023 · similarity 0.85)
- Certification for Differentially Private Prediction in Gradient-Based Training (ICML 2025 · similarity 0.85)
- Selling Data To a Machine Learner: Pricing via Costly Signaling (ICML 2022 · similarity 0.85)
- Public-data Assisted Private Stochastic Optimization: Power and Limitations (NeurIPS 2024 · similarity 0.84)
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.
