English

Optimizing the Performative Risk under Weak Convexity Assumptions

Machine Learning 2022-10-24 v4 Machine Learning

Abstract

In performative prediction, a predictive model impacts the distribution that generates future data, a phenomenon that is being ignored in classical supervised learning. In this closed-loop setting, the natural measure of performance named performative risk (PR\mathrm{PR}), captures the expected loss incurred by a predictive model \emph{after} deployment. The core difficulty of using the performative risk as an optimization objective is that the data distribution itself depends on the model parameters. This dependence is governed by the environment and not under the control of the learner. As a consequence, even the choice of a convex loss function can result in a highly non-convex PR\mathrm{PR} minimization problem. Prior work has identified a pair of general conditions on the loss and the mapping from model parameters to distributions that implies the convexity of the performative risk. In this paper, we relax these assumptions and focus on obtaining weaker notions of convexity, without sacrificing the amenability of the PR\mathrm{PR} minimization problem for iterative optimization methods.

Keywords

Cite

@article{arxiv.2209.00771,
  title  = {Optimizing the Performative Risk under Weak Convexity Assumptions},
  author = {Yulai Zhao},
  journal= {arXiv preprint arXiv:2209.00771},
  year   = {2022}
}

Comments

Neurips 2022 Workshop on Optimization for Machine Learning

R2 v1 2026-06-28T00:36:24.278Z