{
  "abstract": "Chance-constrained programs (CCPs) optimize decisions under uncertainty by limiting the probability of constraint violation. Despite advances in traditional and learning-based approaches, optimizing non-convex or non-smooth objectives and adapting to different objectives under fixed chance constraints remain challenging. In this paper, we propose a \\textbf{D}erivative-free \\textbf{D}iffusion-based framework that \\textbf{D}isentangles constraint modeling from objective optimization, termed \\textbf{D$^3$Opt}. We learn the chance-feasible structure once, independently of any particular objective, by training a risk-conditioned diffusion model solely on constraint-filtered decisions and freezing it as a reusable prior for post-specified objectives. At inference time, we propose an annealed, particle-based Feynman--Kac correction along the frozen reverse diffusion process to optimize post-specified objectives using only function evaluations. This enables derivative-free optimization of non-convex and non-smooth objectives without objective-specific retraining. We prove that the correction preserves feasibility when this property holds for the frozen prior, and derive an optimization-error bound separating learned-prior coverage, finite-particle approximation, and finite-temperature effects. Experiments on linear Gaussian CCPs, objective-transfer tasks, and chance-constrained economic dispatch demonstrate effective optimization across smooth and non-smooth objectives, including non-convex cases, and objective generalization under fixed chance constraints without retraining.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.03071",
  "author_total": 6,
  "authors": [
    {
      "name": "Ziwen Liu"
    },
    {
      "name": "Yan Liu"
    },
    {
      "name": "Congying Han"
    },
    {
      "name": "Tiande Guo"
    },
    {
      "name": "Yao Yan"
    },
    {
      "name": "Weichen Zhao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0fjx4k7bn28z3.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.03071",
  "fulltext_url": null,
  "id": "0fjx4k7bn28z3",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.03071",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.OC"
    ],
    [
      "openalex",
      "1803|Risk and Portfolio Optimization"
    ]
  ],
  "openalex": "W7220470884",
  "pdf_url": "https://arxiv.org/pdf/2610.03071",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0fjx4k7bn28z3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:50Z",
      "native_id": "2610.03071",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.03071"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.OC",
      "subfield": "optimisation-control"
    }
  ],
  "title": "Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained Programming",
  "title_text": "Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained Programming",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:50Z",
  "url": "https://research.draconitic.com/paper/0fjx4k7bn28z3",
  "venue": "arXiv",
  "versions": []
}