Non-linear Welfare-Aware Strategic Learning

arXiv:2405.01810v1 Announce Type: cross
Abstract: This paper studies algorithmic decision-making in the presence of strategic individual behaviors, where an ML model is used to make decisions about human agents and the latter can adapt their behavior strategically to improve their future data. Existing results on strategic learning have largely focused on the linear setting where agents with linear labeling functions best respond to a (noisy) linear decision policy. Instead, this work focuses on general non-linear settings where agents respond to …

abstract adapt agents arxiv behavior cs.ai cs.lg data decision decisions future human linear making non-linear paper results studies type welfare