The paper proposes Decoupled Performative Prediction showing that institutions achieve lower risk by using distinct internal decision models and disclosed models, with an algorithm that converges under standard assumptions and a deception cost metric that self-imposed constraints do not sufficiently
Stochastic optimization schemes for performative prediction with nonconvex loss
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Strategically Deceptive Model Deployment in Performative Prediction
The paper proposes Decoupled Performative Prediction showing that institutions achieve lower risk by using distinct internal decision models and disclosed models, with an algorithm that converges under standard assumptions and a deception cost metric that self-imposed constraints do not sufficiently