AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Bounded-Loss Private Prediction Markets

Rafael Frongillo, Bo Waggoner

NeurIPS 2018 · Federated learning and privacy › Differential privacy · approach: Private online and user-level learning · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add a transaction fee equal to α to the private marketPrivate prediction market · Private prediction marketdesigner budget: unbounded loss -> B_1/λImproved
Replace a fixed-horizon market with adaptively growing stages funded by completed-stage feesTransaction-fee private market · Adaptive private prediction marketdesigner budget: superconstant in T -> boundedImproved
Keep the transaction fee fixed at α across adaptive stagesAdaptive market · Adaptive private prediction marketincentive to trade: 2α-incentive to tradeImproved
Allocate stage precision and failure probabilities as convergent sequencesAdaptive market · Adaptive private prediction marketaccuracy: (α,γ/2), (α/2,γ/4), ... -> (α,γ)Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy