atlas

Research map / Federated learning and privacy / Differential privacy

Revenue-Incentive Tradeoffs in Dynamic Reserve Pricing

ICML 2021 · Federated learning and privacy › Differential privacy · approach: Private data analysis frameworks · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use linear reserve policy (e.g., Myersonian reserve or fixed quantile) instead of non-linear policydynamic reserve pricing (single-buyer, two-stage model) · theory: single-buyer environmentdynamic-IC metric vs normalized revenueHurt
Add a covariance term via Box-Cox weighting with negative lambda (lower lambda) in the non-linear policy (ablation)non-linear Box-Cox reserve policy · synthetic log-normal distribution (no competing bids)revenue-incentive tradeoff (DIC vs Reserve Revenue/Welfare)Helped
Use non-linear Box-Cox policy with lower lambda (e.g., negative lambda) instead of exponential mechanism (lambda=1) (ablation)non-linear Box-Cox reserve policy · real ad exchange data, single bidder (training and testing)revenue-incentive tradeoff (DIC vs Reserve Revenue/Welfare)Helped
Increase lambda to large absolute values or use positive lambda on shifted log-normal distribution (ablation)non-linear Box-Cox reserve policy · synthetic shifted log-normal distributionrevenue-incentive tradeoffHurt
Include competing bids in the simulation (vs single bidder)dynamic reserve pricing on ad auction data · real ad exchange dataDIC rangeHelped

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