Performative Scenario Optimization

TL;DR

This paper develops a framework for decision-dependent chance-constrained optimization, introducing performative solutions as equilibria, with a model-free approximation and an application to AI safety involving LLM jailbreaks.

Contribution

It proposes a novel performative scenario optimization framework with convergence guarantees and demonstrates its effectiveness in AI safety applications.

Findings

Proves existence of performative solutions using fixed-point theory.

Develops a model-free, scenario-based approximation method.

Shows convergence of the method to a stable equilibrium in AI safety context.

Abstract

This paper introduces a performative scenario optimization framework for decision-dependent chance-constrained problems. Unlike classical stochastic optimization, we account for the feedback loop where decisions actively shape the underlying data-generating process. We define performative solutions as self-consistent equilibria and establish their existence using Kakutani's fixed-point theorem. To ensure computational tractability without requiring an explicit model of the environment, we propose a model-free, scenario-based approximation that alternates between data generation and optimization. Under mild regularity conditions, we prove that a stochastic fixed-point iteration, equipped with a logarithmic sample size schedule, converges almost surely to the unique performative solution. The effectiveness of the proposed framework is demonstrated through an emerging AI safety application: deploying performative guardrails against Large Language Model (LLM) jailbreaks. Numerical results confirm the co-evolution and convergence of the guardrail classifier and the induced adversarial prompt distribution to a stable equilibrium.