Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty
Published in NeurIPS 2025
Published in NeurIPS 2025
Published in arXiv preprint, 2025
Strategic learning studies how decision rules interact with agents who may strategically change their inputs/features to achieve better outcomes. This work studies how to incentivize desirable feature changes fairly across heterogeneous agents while preserving the principal’s objective.