A Lagrangian duality method approximates best responses for non-linear strategic classification and enables gradient-based training via the Implicit Function Theorem, yielding improved strategic accuracy on standard datasets.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces a two-stage robust optimization model with decision-dependent uncertainty sets to capture evolving manipulation costs and reduce gaming in strategic classification.
citing papers explorer
-
Non-Linear Strategic Classification Made Practical
A Lagrangian duality method approximates best responses for non-linear strategic classification and enables gradient-based training via the Implicit Function Theorem, yielding improved strategic accuracy on standard datasets.
-
Robust Strategic Classification under Decision-Dependent Cost Uncertainty
Introduces a two-stage robust optimization model with decision-dependent uncertainty sets to capture evolving manipulation costs and reduce gaming in strategic classification.