AI Paper Atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning

Neehar Peri, Michael Curry, Samuel Dooley, John P Dickerson

NeurIPS 2021 · Learning theory and algorithms › Submodular and game algorithms · approach: Learned auction design · 8 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
Learn the quota constraint from exemplars rather than optimize it explicitlyPreferenceNet vs RegretNet · 4x2 unit-demand auctionPCA: .1 -> 100.0Improved
Learn the quota constraint from exemplars rather than optimize it explicitlyPreferenceNet vs RegretNet · 2x2 additive auctionPCA: 75.1 -> 100.0Improved
Use PreferenceNet to enforce quotaPreferenceNet · 4x4 additive auctionPCA: 0 -> 0No clear effect
Learn preferences from exemplars instead of explicitly optimizing the known constraintPreferenceNet vs RegretNet · Synthetic fairness auctionsPCA: 2x2 unit-demand TVF: 100.0 -> 100.0; 4x2 unit-demand quota: .1 -> 100.0; 4x4 additive quota: 0 -> 0Mixed
Add label noise following the probit model (ablation)PreferenceNet · 2-agent, 2-item auctions; synthetic preference labelsPCA: 25%Hurt
Add label noise following the probit model (ablation)PreferenceNet · 2-agent, 2-item auctions; synthetic preference labelsmean regret: 25%No clear effect
Enforce preference loss with augmented Lagrangian multipliers (ablation)PreferenceNet · Synthetic fairness auctionsmean regretHurt
Enforce preference loss with augmented Lagrangian multipliers (ablation)PreferenceNet · Synthetic fairness auctionsmean paymentsHurt
Enforce preference loss with augmented Lagrangian multipliers (ablation)PreferenceNet · Synthetic fairness auctionsPCA: 4x4 additive quota: 0 -> .1Mixed
Add preference MLP training and co-trainingPreferenceNet · TVF auctions, 1x2 additivetraining time: 28m -> 43mHurt
Train on mixtures of TVF, entropy, and quota preference labels (ablation)PreferenceNet · Additive auctions, mixed synthetic preferencesaverage PCA: 78.8; 99.9; 16.0; 64.4Mixed
Use PreferenceNet rather than RegretNet under asymmetric valuations2x2 auction · 2x2 asymmetric valuations, quotaPCA: 39.2 -> 100.0; 27.3 -> 100.0; 17.1 -> 100.0Improved

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