Fast Online Distributionally Robust Optimization via Data Compression

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Irina, Fochesato, Marta, Stellato, Bartolomeo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908531152650240
author Wang, Irina
Fochesato, Marta
Stellato, Bartolomeo
author_facet Wang, Irina
Fochesato, Marta
Stellato, Bartolomeo
contents We propose an online data compression approach for efficiently solving distributionally robust optimization (DRO) problems with streaming data while maintaining out-of-sample performance guarantees. Our method dynamically constructs ambiguity sets using online clustering, allowing the clustered configuration to evolve over time for an accurate representation of the underlying distribution. We establish theoretical conditions for clustering algorithms to ensure robustness, and show that the performance gap between our online solution and the nominal DRO solution can be written in terms of the distance between the true and compressed distributions. Therefore, by varying the number of clusters, our method effectively balances robustness and online computational efficiency. We show that our analysis is compatible with well-established finite-sample and asymptotic guarantees for Wasserstein DRO. Numerical experiments in mixed-integer portfolio optimization demonstrate significant computational savings, with minimal loss in solution quality.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08097
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast Online Distributionally Robust Optimization via Data Compression
Wang, Irina
Fochesato, Marta
Stellato, Bartolomeo
Optimization and Control
We propose an online data compression approach for efficiently solving distributionally robust optimization (DRO) problems with streaming data while maintaining out-of-sample performance guarantees. Our method dynamically constructs ambiguity sets using online clustering, allowing the clustered configuration to evolve over time for an accurate representation of the underlying distribution. We establish theoretical conditions for clustering algorithms to ensure robustness, and show that the performance gap between our online solution and the nominal DRO solution can be written in terms of the distance between the true and compressed distributions. Therefore, by varying the number of clusters, our method effectively balances robustness and online computational efficiency. We show that our analysis is compatible with well-established finite-sample and asymptotic guarantees for Wasserstein DRO. Numerical experiments in mixed-integer portfolio optimization demonstrate significant computational savings, with minimal loss in solution quality.
title Fast Online Distributionally Robust Optimization via Data Compression
topic Optimization and Control
url https://arxiv.org/abs/2504.08097