Research map / Learning theory and algorithms / Submodular and game algorithms
Welfare-Optimal Classification with Accuracy Auctions
Bana Sadi, Eden Saig, Nir Rosenfeld
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 |
|---|---|---|---|
| optimize welfare with elicited values instead of accuracy | linear classifier · ACSIncome feature-based values | welfare: up to 5% | Improved |
| optimize welfare with label-based values instead of accuracy | linear classifier · ACSIncome label-based values | welfare: +23% | Improved |
| optimize welfare with label-based values instead of accuracy | linear classifier · ACSIncome label-based values | accuracy: -21% | Hurt |
| increase training set size m | accuracy auction with linear classifiers · Gaussian synthetic data | number of paying users | No clear effect |
| increase training set size m | accuracy auction with hinge, squared hinge, log loss · ACSIncome label-based values | number of paying users: at most 20; proportion decays from 1.5% towards zero | No clear effect |
| increase class separation (higher attainable accuracy) (ablation) | accuracy auction · Gaussian synthetic data | fraction of paying users | Improved |
| increase noise sigma (less separable data) (ablation) | accuracy auction · Gaussian synthetic data | number of paying users | Hurt |
Closest papers by meaning
- Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility (NeurIPS 2026 · similarity 0.87)
- The Hidden Cost of Waiting for Accurate Predictions (ICLR 2025 · similarity 0.87)
- The Relative Value of Prediction in Algorithmic Decision Making (ICML 2024 · similarity 0.86)
- Fair and Welfare-Efficient Constrained Multi-Matchings under Uncertainty (NeurIPS 2024 · similarity 0.86)
- Learning Classifiers That Induce Markets (ICML 2025 · similarity 0.85)
- Multidimensional Bayesian Utility Maximization: Tight Approximations to Welfare (NeurIPS 2025 · similarity 0.85)
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.
