AI Paper Atlas

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

Welfare-Optimal Classification with Accuracy Auctions

Bana Sadi, Eden Saig, Nir Rosenfeld

ICML 2026 · Learning theory and algorithms › Submodular and game algorithms · approach: Matching markets and welfare · 0 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
optimize welfare with elicited values instead of accuracylinear classifier · ACSIncome feature-based valueswelfare: up to 5%Improved
optimize welfare with label-based values instead of accuracylinear classifier · ACSIncome label-based valueswelfare: +23%Improved
optimize welfare with label-based values instead of accuracylinear classifier · ACSIncome label-based valuesaccuracy: -21%Hurt
increase training set size maccuracy auction with linear classifiers · Gaussian synthetic datanumber of paying usersNo clear effect
increase training set size maccuracy auction with hinge, squared hinge, log loss · ACSIncome label-based valuesnumber of paying users: at most 20; proportion decays from 1.5% towards zeroNo clear effect
increase class separation (higher attainable accuracy) (ablation)accuracy auction · Gaussian synthetic datafraction of paying usersImproved
increase noise sigma (less separable data) (ablation)accuracy auction · Gaussian synthetic datanumber of paying usersHurt

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