Adaptive Gradient-Based Methods for a Broader Class of Optimization Problems under Performative Prediction
Abstract
We study optimization under performative prediction, where deploying a model affects the future data distribution. For this setting, several gradient-based approaches have been proposed. However, they typically assume specific data distributions or loss functions, which limit their practical applicability. To overcome these limitations, we propose a gradient-based optimization method with convergence guarantees under substantially weaker assumptions. Our method explicitly estimates the induced distribution shift through finite differences. It enables higher-dimensional optimization across broader classes of loss functions and data distributions. We also propose a practical variant that reduces the number of samples required. Numerical experiments demonstrate that our proposed algorithms converge faster and more consistently than existing ones.
Cite
@article{arxiv.2607.26562,
title = {Adaptive Gradient-Based Methods for a Broader Class of Optimization Problems under Performative Prediction},
author = {Hiroki Hamaguchi and Yuya Hikima and Hiroshi Sawada and Akiko Takeda},
journal= {arXiv preprint arXiv:2607.26562},
year = {2026}
}
Comments
31pages, 2 figures