Ambiguous Strategic Classification

2026-06-08

AI Summary

This work addresses strategic classification settings where regulatory requirements often mandate only partial disclosure of the classifier rather than full transparency. Introducing, for the first time, the concept of “ambiguity” from mechanism design into this framework, the paper allows the learner to publicly announce a set of plausible classifiers while privately selecting one, thereby preserving strategic flexibility under disclosure constraints. The authors develop a novel paradigm that integrates ambiguity modeling, game-theoretic best-response computation, and efficient training, and propose a scalable algorithm to jointly optimize classification performance and strategic response. Experimental results demonstrate that the proposed approach significantly outperforms existing baselines in strategic environments, exhibiting both practical feasibility and superior performance.

Abstract

A common assumption in strategic classification is that the classifier is public knowledge. However, it remains unclear whether, and why, a system would choose to commit to full disclosure. We study a setting in which regulation requires the system to disclose some, but not all, of the information. This induces a learning task in which the learner must jointly optimize the classifier and the uncertainty surrounding it. To this end, we adopt from robust mechanism design the notion of ambiguity, which in our setting allows the learner to reveal a set or range of possible classifiers, while privately choosing which of them to ultimately realize. We investigate how ambiguity affects the learning task, develop efficient algorithms for computing best-responses and training, and empirically explore strategic learning and its outcomes in this novel setting and using our approach.

Problem

• strategic classification
• ambiguity
• partial disclosure
• robust mechanism design
• classifier uncertainty

Innovation

• Ambiguous Strategic Classification
• Partial Disclosure
• Robust Mechanism Design
• Strategic Learning
• Classifier Uncertainty