Research map / Learning theory and algorithms / Prediction and decision losses
Sequential Strategic Screening
Lee Cohen, Saeed Sharifi -Malvajerdi, Kevin Stangl, Ali Vakilian, Juba Ziani
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 |
|---|---|---|---|
| Use sequential screening instead of conjunctive screening | Agent manipulation in a screening pipeline · Two-classifier example | manipulation cost: \sqrt{2} -> 5/4 | Improved |
| Allow sequential manipulation rather than requiring a single point to pass all classifiers | Agent manipulation in linear-classifier pipelines · General sequence of classifiers | minimum manipulation cost | Improved |
| Use sequential screening when the angle between two classifier regions is at least \pi/2 | Two-dimensional, two-classifier screening · Two linear classifiers with angle \pi/2 or greater | minimum manipulation cost | No clear effect |
| Use monotone classifiers with norm-based manipulation costs | Sequential screening · Monotone classifier sequences | minimum manipulation cost | No clear effect |
| Apply the conservative defense by shifting each linear threshold by the manipulation budget | Firm's sequential screening pipeline · Linear classifiers in general position | true positive rate subject to zero false positives | Improved |
| Use sequential rather than conjunctive screening under the conservative defense | Firm's screening process · Linear classifiers in general position | true positive rate | Improved |
Closest papers by meaning
- One-Shot Strategic Classification Under Unknown Costs (ICML 2024 · similarity 0.84)
- Bayesian Strategic Classification (NeurIPS 2024 · similarity 0.84)
- Strategic Classification with Non-Linear Classifiers (NeurIPS 2025 · similarity 0.84)
- Classification Under Strategic Self-Selection (ICML 2024 · similarity 0.84)
- Sequential Kernel Goodness-of-fit Testing (ICML 2024 · similarity 0.84)
- Strategic Classification With Externalities (ICLR 2025 · similarity 0.83)
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.
