Strategic Classification with Non-Linear Classifiers
This work addresses the challenge of modeling strategic user behavior in machine learning for applications like fraud detection or credit scoring, representing a foundational extension beyond linear classifiers.
The paper tackles the problem of strategic classification with non-linear classifiers, showing that strategic behavior can either increase or decrease effective class complexity arbitrarily and that universal approximators like neural nets lose their universality in strategic environments, leading to performance gaps.
In strategic classification, the standard supervised learning setting is extended to support the notion of strategic user behavior in the form of costly feature manipulations made in response to a classifier. While standard learning supports a broad range of model classes, the study of strategic classification has, so far, been dedicated mostly to linear classifiers. This work aims to expand the horizon by exploring how strategic behavior manifests under non-linear classifiers and what this implies for learning. We take a bottom-up approach showing how non-linearity affects decision boundary points, classifier expressivity, and model class complexity. Our results show how, unlike the linear case, strategic behavior may either increase or decrease effective class complexity, and that the complexity decrease may be arbitrarily large. Another key finding is that universal approximators (e.g., neural nets) are no longer universal once the environment is strategic. We demonstrate empirically how this can create performance gaps even on an unrestricted model class.