Distributionally Robust Optimisation with Bayesian Ambiguity Sets

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dellaporta, Charita, O'Hara, Patrick, Damoulas, Theodoros
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912015883173888
author Dellaporta, Charita
O'Hara, Patrick
Damoulas, Theodoros
author_facet Dellaporta, Charita
O'Hara, Patrick
Damoulas, Theodoros
contents Decision making under uncertainty is challenging since the data-generating process (DGP) is often unknown. Bayesian inference proceeds by estimating the DGP through posterior beliefs about the model's parameters. However, minimising the expected risk under these posterior beliefs can lead to sub-optimal decisions due to model uncertainty or limited, noisy observations. To address this, we introduce Distributionally Robust Optimisation with Bayesian Ambiguity Sets (DRO-BAS) which hedges against uncertainty in the model by optimising the worst-case risk over a posterior-informed ambiguity set. We show that our method admits a closed-form dual representation for many exponential family members and showcase its improved out-of-sample robustness against existing Bayesian DRO methodology in the Newsvendor problem.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03492
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Distributionally Robust Optimisation with Bayesian Ambiguity Sets
Dellaporta, Charita
O'Hara, Patrick
Damoulas, Theodoros
Machine Learning
Decision making under uncertainty is challenging since the data-generating process (DGP) is often unknown. Bayesian inference proceeds by estimating the DGP through posterior beliefs about the model's parameters. However, minimising the expected risk under these posterior beliefs can lead to sub-optimal decisions due to model uncertainty or limited, noisy observations. To address this, we introduce Distributionally Robust Optimisation with Bayesian Ambiguity Sets (DRO-BAS) which hedges against uncertainty in the model by optimising the worst-case risk over a posterior-informed ambiguity set. We show that our method admits a closed-form dual representation for many exponential family members and showcase its improved out-of-sample robustness against existing Bayesian DRO methodology in the Newsvendor problem.
title Distributionally Robust Optimisation with Bayesian Ambiguity Sets
topic Machine Learning
url https://arxiv.org/abs/2409.03492