Adaptive Gradient-Based Methods for a Broader Class of Optimization Problems under Performative Prediction
Hiroki Hamaguchi, Yuya Hikima, Hiroshi Sawada, Akiko Takeda
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.
Topics
Classified with taxonomy v2 on Sat, 5 Sept 2026.