When In Doubt, Abstain: The Impact of Abstention on Strategic Classification
- URL: http://arxiv.org/abs/2510.13327v3
- Date: Thu, 30 Oct 2025 21:41:25 GMT
- Title: When In Doubt, Abstain: The Impact of Abstention on Strategic Classification
- Authors: Lina Alkarmi, Ziyuan Huang, Mingyan Liu,
- Abstract summary: This paper studies abstention within a strategic classification context.<n>We show that optimal abstention ensures that the principal's utility is no worse than in a non-abstention setting.<n>We also show that abstention can also serve as a deterrent to manipulation, making it costlier for agents to manipulate to achieve a positive outcome.
- Score: 11.395181681423892
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Algorithmic decision making is increasingly prevalent, but often vulnerable to strategic manipulation by agents seeking a favorable outcome. Prior research has shown that classifier abstention (allowing a classifier to decline making a decision due to insufficient confidence) can significantly increase classifier accuracy. This paper studies abstention within a strategic classification context, exploring how its introduction impacts strategic agents' responses and how principals should optimally leverage it. We model this interaction as a Stackelberg game where a principal, acting as the classifier, first announces its decision policy, and then strategic agents, acting as followers, manipulate their features to receive a desired outcome. Here, we focus on binary classifiers where agents manipulate observable features rather than their true features, and show that optimal abstention ensures that the principal's utility (or loss) is no worse than in a non-abstention setting, even in the presence of strategic agents. We also show that beyond improving accuracy, abstention can also serve as a deterrent to manipulation, making it costlier for agents, especially those less qualified, to manipulate to achieve a positive outcome when manipulation costs are significant enough to affect agent behavior. These results highlight abstention as a valuable tool for reducing the negative effects of strategic behavior in algorithmic decision making systems.
Related papers
- Desirable Effort Fairness and Optimality Trade-offs in Strategic Learning [4.702729080310267]
We study how decision rules interact with agents who may strategically change their inputs/features to achieve better outcomes.<n>We propose a unified model of principal-agent interaction that captures this trade-off.
arXiv Detail & Related papers (2025-10-21T21:43:20Z) - Collective dynamics of strategic classification [49.14942990735098]
We apply evolutionary game theory to the problem of feedback loops between collectives of users and institutions.<n>We show that increased detection capabilities reduce social costs and could lead to users' improvement.<n>The speed at which the institutions re-adapt to the user's population plays a role in the final outcome.
arXiv Detail & Related papers (2025-08-12T20:57:17Z) - Learning to Lead: Incentivizing Strategic Agents in the Dark [50.93875404941184]
We study an online learning version of the generalized principal-agent model.<n>We develop the first provably sample-efficient algorithm for this challenging setting.<n>We establish a near optimal $tildeO(sqrtT) $ regret bound for learning the principal's optimal policy.
arXiv Detail & Related papers (2025-06-10T04:25:04Z) - Anticipating Gaming to Incentivize Improvement: Guiding Agents in (Fair) Strategic Classification [6.660458629649826]
We explore individuals' choice between genuinely improving their qualifications ('improvement'') vs. attempting to deceive the algorithm.<n>We formulate these interactions as a Stackelberg game, where a firm deploys a (fair) classifier, and individuals strategically respond.
arXiv Detail & Related papers (2025-05-08T18:47:23Z) - Strategic Classification With Externalities [11.36782598786846]
We propose a new variant of the strategic classification problem.<n>Motivated by real-world applications, our model crucially allows the manipulation of one agent to affect another.<n>We show that under certain assumptions, the pure Nash Equilibrium of this agent manipulation game is unique and can be efficiently computed.
arXiv Detail & Related papers (2024-10-10T15:28:04Z) - Criticality and Safety Margins for Reinforcement Learning [53.10194953873209]
We seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users.<n>We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions.<n>We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality.
arXiv Detail & Related papers (2024-09-26T21:00:45Z) - Classification Under Strategic Self-Selection [13.168262355330299]
We study the effects of self-selection on learning and the implications of learning on the composition of the self-selected population.
We propose a differentiable framework for learning under self-selective behavior, which can be optimized effectively.
arXiv Detail & Related papers (2024-02-23T11:37:56Z) - Who Leads and Who Follows in Strategic Classification? [82.44386576129295]
We argue that the order of play in strategic classification is fundamentally determined by the relative frequencies at which the decision-maker and the agents adapt to each other's actions.
We show that a decision-maker with the freedom to choose their update frequency can induce learning dynamics that converge to Stackelberg equilibria with either order of play.
arXiv Detail & Related papers (2021-06-23T16:48:46Z) - Learning Strategies in Decentralized Matching Markets under Uncertain
Preferences [91.3755431537592]
We study the problem of decision-making in the setting of a scarcity of shared resources when the preferences of agents are unknown a priori.
Our approach is based on the representation of preferences in a reproducing kernel Hilbert space.
We derive optimal strategies that maximize agents' expected payoffs.
arXiv Detail & Related papers (2020-10-29T03:08:22Z) - Catch Me if I Can: Detecting Strategic Behaviour in Peer Assessment [61.24399136715106]
We consider the issue of strategic behaviour in various peer-assessment tasks, including peer grading of exams or homeworks and peer review in hiring or promotions.
Our focus is on designing methods for detection of such manipulations.
Specifically, we consider a setting in which agents evaluate a subset of their peers and output rankings that are later aggregated to form a final ordering.
arXiv Detail & Related papers (2020-10-08T15:08:40Z) - Causal Strategic Linear Regression [5.672132510411465]
In many predictive decision-making scenarios, such as credit scoring and academic testing, a decision-maker must construct a model that accounts for agents' propensity to "game" the decision rule.
We join concurrent work in modeling agents' outcomes as a function of their changeable attributes.
We provide efficient algorithms for learning decision rules that optimize three distinct decision-maker objectives.
arXiv Detail & Related papers (2020-02-24T03:57:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.