Sequential Strategic Screening
Not on the map. Why?
Abstract (arXiv)
We initiate the study of strategic behavior in screening processes with multiple classifiers. We focus on two contrasting settings: a conjunctive setting in which an individual must satisfy all classifiers simultaneously, and a sequential setting in which an individual to succeed must satisfy classifiers one at a time. In other words, we introduce the combination of strategic classification with screening processes. We show that sequential screening pipelines exhibit new and surprising behavior where individuals can exploit the sequential ordering of the tests to zig-zag between classifiers without having to simultaneously satisfy all of them. We demonstrate an individual can obtain a positive outcome using a limited manipulation budget even when far from the intersection of the positive regions of every classifier. Finally, we consider a learner whose goal is to design a sequential screening process that is robust to such manipulations, and provide a construction for the learner that optimizes a natural objective.
Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 35 of its 52 references that are in the map. First posted on arXiv 31 Jan 2023.
Builds on
35 of 52 references.
References · 35
- 2018Actionable Recourse in Linear Classificationcited by 327
- 2020Performative Predictioncited by 318
- 2015Strategic Classificationcited by 256
- 2017Strategic Classification from Revealed Preferencescited by 126
- 2018The Social Cost of Strategic Classificationcited by 105
- 2019Strategic Classification is Causal Modeling in Disguisecited by 92
- 2018How Do Classifiers Induce Agents To Invest Effort Strategically?cited by 82
- 2018The Disparate Effects of Strategic Manipulationcited by 75
- 2021Strategic Classification in the Darkcited by 66
- 2020Causal Strategic Linear Regressioncited by 65
- 2013Online Learning with Switching Costs and Other Adaptive Adversariescited by 60
- 2020The Strategic Perceptroncited by 48
23 more
- 2021Information Discrepancy in Strategic Learningcited by 48
- 2021Alternative Microfoundations for Strategic Classificationcited by 47
- 2020Maximizing Welfare with Incentive-Aware Evaluation Mechanismscited by 46
- 2018Fairness Under Compositioncited by 43
- 2019The Disparate Equilibria of Algorithmic Decision Making when Individuals Invest Rationallycited by 41
- 2020The Role of Randomness and Noise in Strategic Classificationcited by 40
- 2021Stateful Strategic Regressioncited by 32
- 2018Online Optimization with Predictions and Switching Costs: Fast Algorithms and the Fundamental Limitcited by 27
- 2022On classification of strategic agents who can both game and improvecited by 27
- 2018Strategyproof Linear Regression in High Dimensionscited by 22
- 2020Individual Fairness in Pipelinescited by 22
- 2017Fair Pipelinescited by 21
- 2018Chasing Nested Convex Bodies Nearly Optimallycited by 21
- 2019Optimal Decision Making Under Strategic Behaviorcited by 20
- 2020Manipulation-Proof Machine Learningcited by 19
- 2019Chasing Convex Bodies Optimallycited by 18
- 2019Efficient candidate screening under multiple tests and implications for fairnesscited by 16
- 2019Chasing Convex Bodies with Linear Competitive Ratiocited by 15
- 2015Truthful Linear Regressioncited by 12
- 2017Nested Convex Bodies are Chaseablecited by 8
- 2022Multi Stage Screening: Enforcing Fairness and Maximizing Efficiency in a Pre-Existing Pipelinecited by 8
- 2018Competitively Chasing Convex Bodiescited by 7
- 2020Pipeline Interventionscited by 4
Built on by
Citing papers per year: 2024: 4; 2025: 2; 2026: 2.
8 papers.
- 2024Learnability Gaps of Strategic Classificationcited by 16
- 2024Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classificationcited by 8
- 2024Classification Under Strategic Self-Selectioncited by 7
- 2025Explanation Design in Strategic Learning: Sufficient Explanations that Induce Non-harmful Responsescited by 1
- 2025The Disparate Effects of Partial Information in Bayesian Strategic Learningcited by 1
- 2026Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamicscited by 1
- 2024Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model Systemcited by 0
- 2026Linear Strategic Classification with Endogenous Improvementscited by 0
- 2026Linear Strategic Classification with Endogenous Improvements31 May 2026
- 2026Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics11 Feb 2026
- 2025The Disparate Effects of Partial Information in Bayesian Strategic Learning31 May 2025
- 2025Explanation Design in Strategic Learning: Sufficient Explanations that Induce Non-harmful Responses6 Feb 2025
- 2024Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System30 Oct 2024
- 2024Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification16 Jul 2024
- 2024Learnability Gaps of Strategic Classification29 Feb 2024
- 2024Classification Under Strategic Self-Selection23 Feb 2024