mlsanityData to 7 Oct 2026

Distributionally Robust Optimization via Diffusion Ambiguity Modeling

arXiv 2510.22757 ↗First posted 26 Oct 2025cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 28 of its 40 references that are in the map. First posted on arXiv 26 Oct 2025.

Builds on

28 of 40 references.

References · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  6. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  7. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  8. 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 285
  9. 2016Distributionally Robust Stochastic Optimization with Wasserstein Distancecited by 182
  10. 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 169
  11. 2018Learning to Learn from Noisy Labeled Datacited by 160
  12. 2017Learning From Noisy Large-Scale Datasets With Minimal Supervisioncited by 115
16 more
  1. 2020Distributionally Robust Bayesian Optimizationcited by 60
  2. 2021Out of Distribution Generalization in Machine Learningcited by 59
  3. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  4. 2023AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Modelscited by 46
  5. 2021Distributionally Robust Learningcited by 44
  6. 2019Distributionally Robust Reinforcement Learningcited by 40
  7. 2017Global optimality conditions for deep neural networkscited by 31
  8. 2025Gen-DFL: Decision-Focused Generative Learning for Robust Decision Makingcited by 18
  9. 2021Distributionally Robust Policy Learning via Adversarial Environment Generationcited by 17
  10. 2022Distributionally Robust Bayesian Optimization with varphi-divergencescited by 16
  11. 2023Flow-based Distributionally Robust Optimizationcited by 13
  12. 2024Differentiable Distributionally Robust Optimization Layerscited by 8
  13. 2024Distributionally Robust Optimization via Iterative Algorithms in Continuous Probability Spacescited by 8
  14. 2021Adversarial Deep Learning for Online Resource Allocationcited by 7
  15. 2020Conic Reformulations for Kullback-Leibler Divergence Constrained Distributionally Robust Optimization and Applicationscited by 4
  16. 2025Nested Stochastic Algorithm for Generalized Sinkhorn distance-Regularized Distributionally Robust Optimizationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Worst-case generation via minimax optimization in Wasserstein spacecited by 7
  2. 2026Constrained Diffusion Models with Primal-Dual Inferencecited by 2
  3. 2025Iterative Sampling Methods for Sinkhorn Distributionally Robust Optimizationcited by 1
  4. 2026Generative Distributionally Robust Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Distributionally Robust Optimization via Generative Ambiguity Modeling
  2. 2025Improved Diffusion-based Generative Model with Better Adversarial Robustness
  3. 20263D-Learning: Diffusion-Augmented Distributionally Robust Decision-Focused Learning
  4. 2026Robustness of Diffusion Models under Distribution Shift
  5. 2025SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion
  6. 2023Robust Classification via a Single Diffusion Model
  7. 2025Direct Distributional Optimization for Provable Alignment of Diffusion Models
  8. 2023Diffusion Models are Minimax Optimal Distribution Estimators