Score: 0

Distributionally Robust Optimization via Diffusion Ambiguity Modeling

Published: October 26, 2025 | arXiv ID: 2510.22757v1

By: Jiaqi Wen, Jianyi Yang

Potential Business Impact:

Makes computer learning better with new data.

Business Areas:
A/B Testing Data and Analytics

This paper studies Distributionally Robust Optimization (DRO), a fundamental framework for enhancing the robustness and generalization of statistical learning and optimization. An effective ambiguity set for DRO must involve distributions that remain consistent with the nominal distribution while being diverse enough to account for a variety of potential scenarios. Moreover, it should lead to tractable DRO solutions. To this end, we propose a diffusion-based ambiguity set design that captures various adversarial distributions beyond the nominal support space while maintaining consistency with the nominal distribution. Building on this ambiguity modeling, we propose Diffusion-based DRO (D-DRO), a tractable DRO algorithm that solves the inner maximization over the parameterized diffusion model space. We formally establish the stationary convergence performance of D-DRO and empirically demonstrate its superior Out-of-Distribution (OOD) generalization performance in a ML prediction task.

Country of Origin
🇺🇸 United States

Page Count
28 pages

Category
Computer Science:
Machine Learning (CS)