Computing Strategic Responses to Non-Linear Classifiers
By: Jack Geary, Boyan Gao, Henry Gouk
Potential Business Impact:
Helps computers learn when people try to trick them.
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.
Similar Papers
How Strategic Agents Respond: Comparing Analytical Models with LLM-Generated Responses in Strategic Classification
Machine Learning (CS)
Helps AI learn to make fair decisions with advice.
Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
CS and Game Theory
Hiding a system's rules can make it worse.
Anticipating Gaming to Incentivize Improvement: Guiding Agents in (Fair) Strategic Classification
Machine Learning (CS)
Helps computers trick people into being better.