One-Shot Strategic Classification Under Unknown Costs

arXiv:2311.02761v2 Announce Type: replace
Abstract: The goal of strategic classification is to learn decision rules which are robust to strategic input manipulation. Earlier works assume that these responses are known; while some recent works handle unknown responses, they exclusively study online settings with repeated model deployments. But there are many domains$\unicode{x2014}$particularly in public policy, a common motivating use case$\unicode{x2014}$where multiple deployments are infeasible, or where even one bad round is unacceptable. To address this gap, we initiate the formal study …

abstract arxiv classification costs cs.gt cs.lg decision deployments domains learn manipulation policy public public policy responses robust rules stat.ml study type unicode