Alternative Microfoundations for Strategic Classification

by   Meena Jagadeesan, et al.

When reasoning about strategic behavior in a machine learning context it is tempting to combine standard microfoundations of rational agents with the statistical decision theory underlying classification. In this work, we argue that a direct combination of these standard ingredients leads to brittle solution concepts of limited descriptive and prescriptive value. First, we show that rational agents with perfect information produce discontinuities in the aggregate response to a decision rule that we often do not observe empirically. Second, when any positive fraction of agents is not perfectly strategic, desirable stable points – where the classifier is optimal for the data it entails – cease to exist. Third, optimal decision rules under standard microfoundations maximize a measure of negative externality known as social burden within a broad class of possible assumptions about agent behavior. Recognizing these limitations we explore alternatives to standard microfoundations for binary classification. We start by describing a set of desiderata that help navigate the space of possible assumptions about how agents respond to a decision rule. In particular, we analyze a natural constraint on feature manipulations, and discuss properties that are sufficient to guarantee the robust existence of stable points. Building on these insights, we then propose the noisy response model. Inspired by smoothed analysis and empirical observations, noisy response incorporates imperfection in the agent responses, which we show mitigates the limitations of standard microfoundations. Our model retains analytical tractability, leads to more robust insights about stable points, and imposes a lower social burden at optimality.


page 1

page 2

page 3

page 4


Who Leads and Who Follows in Strategic Classification?

As predictive models are deployed into the real world, they must increas...

Strategic Classification in the Dark

Strategic classification studies the interaction between a classificatio...

The Social Cost of Strategic Classification

Consequential decision-making typically incentivizes individuals to beha...

Learning Losses for Strategic Classification

Strategic classification, i.e. classification under possible strategic m...

Formalizing the Boundary Between Strategic and Nonstrategic Reasoning

Research in multiagent systems often does not draw a clear distinction b...

Causal Strategic Learning with Competitive Selection

We study the problem of agent selection in causal strategic learning und...

Sampling Unknown Decision Functions to Build Classifier Copies

Copies have been proposed as a viable alternative to endow machine learn...

Please sign up or login with your details

Forgot password? Click here to reset