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
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.