Saved in:
Bibliographic Details
Main Authors: Shrivastava, Siddharth, Akshintala, Mahvith, Reddy, B Vamsha Vardhan, Manwani, Naresh, Gujar, Sujit, Ghalme, Ganesh
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2606.01198
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Strategic classification studies settings in which agents respond to a deployed classifier by modifying observable features at a cost. Classical models typically treat such responses as cosmetic: features may change, but true labels remain fixed. We study an improvement-aware variant in which strategic responses can induce genuine changes in outcome-relevant features. Agents choose post-deployment feature vectors strategically, and labels are then generated according to a stable conditional outcome law that preserves the relationship between features and outcomes. We formalize this problem for linear classifiers under a single-index qualification model and linear-decomposable costs. We show that the strategic-optimal classifier is obtained by a parallel shift of the Bayes-optimal decision boundary, and that it provides a better surrogate for the improvement-aware objective than the Bayes classifier. Since improvement-aware learning requires post-deployment labels, which are typically unavailable before deployment, we provide PAC-style guar- antees under an oracle model, propose a practical plug-in algorithm, establish its generalization bound, and evaluate it on synthetic and real-world datasets.