Computing Strategic Responses to Non-Linear Classifiers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Geary, Jack, Gao, Boyan, Gouk, Henry
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908677197266944
author Geary, Jack
Gao, Boyan
Gouk, Henry
author_facet Geary, Jack
Gao, Boyan
Gouk, Henry
contents We consider the problem of strategic classification, where the act of deploying a classifier leads to strategic behaviour that induces a distribution shift on subsequent observations. Current approaches to learning classifiers in strategic settings are focused primarily on the linear setting, but in many cases non-linear classifiers are more suitable. A central limitation to progress for non-linear classifiers arises from the inability to compute best responses in these settings. We present a novel method for computing the best response by optimising the Lagrangian dual of the Agents' objective. We demonstrate that our method reproduces best responses in linear settings, identifying key weaknesses in existing approaches. We present further results demonstrating our method can be straight-forwardly applied to non-linear classifier settings, where it is useful for both evaluation and training.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21560
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Computing Strategic Responses to Non-Linear Classifiers
Geary, Jack
Gao, Boyan
Gouk, Henry
Machine Learning
We consider the problem of strategic classification, where the act of deploying a classifier leads to strategic behaviour that induces a distribution shift on subsequent observations. Current approaches to learning classifiers in strategic settings are focused primarily on the linear setting, but in many cases non-linear classifiers are more suitable. A central limitation to progress for non-linear classifiers arises from the inability to compute best responses in these settings. We present a novel method for computing the best response by optimising the Lagrangian dual of the Agents' objective. We demonstrate that our method reproduces best responses in linear settings, identifying key weaknesses in existing approaches. We present further results demonstrating our method can be straight-forwardly applied to non-linear classifier settings, where it is useful for both evaluation and training.
title Computing Strategic Responses to Non-Linear Classifiers
topic Machine Learning
url https://arxiv.org/abs/2511.21560