Regret Minimization with Performative Feedback
This addresses the challenge of regret minimization in dynamic environments with performative feedback, offering a novel approach for applications like algorithmic decision-making, though it is incremental in leveraging bandit tools.
The paper tackles the problem of finding near-optimal models in performative prediction, where model deployment shifts data distributions, by developing an algorithm that achieves regret bounds scaling only with distribution shift complexity, not reward function complexity, and ensures the final iterate is near-optimal.
In performative prediction, the deployment of a predictive model triggers a shift in the data distribution. As these shifts are typically unknown ahead of time, the learner needs to deploy a model to get feedback about the distribution it induces. We study the problem of finding near-optimal models under performativity while maintaining low regret. On the surface, this problem might seem equivalent to a bandit problem. However, it exhibits a fundamentally richer feedback structure that we refer to as performative feedback: after every deployment, the learner receives samples from the shifted distribution rather than only bandit feedback about the reward. Our main contribution is an algorithm that achieves regret bounds scaling only with the complexity of the distribution shifts and not that of the reward function. The algorithm only relies on smoothness of the shifts and does not assume convexity. Moreover, its final iterate is guaranteed to be near-optimal. The key algorithmic idea is careful exploration of the distribution shifts that informs a novel construction of confidence bounds on the risk of unexplored models. More broadly, our work establishes a conceptual approach for leveraging tools from the bandits literature for the purpose of regret minimization with performative feedback.