Metraipolis › archive › dc_8b612c86ea4d

Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained Programming — arXiv:2610.03071

Source
arXiv
Original
https://arxiv.org/abs/2610.03071
License (as archived)
CC0-1.0
Archived
2026-10-05T23:10:06.731Z
SHA-256 of the archived text
c22be1a8dee415f176ce788a75e721a54350503a4dfe04fc04f8d8bdbb102c8e
Stable URL of this page
https://metraipolis.com/documento/dc_8b612c86ea4d

How to cite

Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained Programming — arXiv:2610.03071 — arXiv, https://arxiv.org/abs/2610.03071 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b612c86ea4d (Metraipolis archive dc_8b612c86ea4d, sha256 c22be1a8dee415f176ce788a75e721a54350503a4dfe04fc04f8d8bdbb102c8e)
BibTeX
@misc{dc8b612c86ea4d,
  title = {Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained Programming — arXiv:2610.03071},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03071},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b612c86ea4d; sha256 c22be1a8dee415f176ce788a75e721a54350503a4dfe04fc04f8d8bdbb102c8e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03071. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.03071 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T23:01:38.667Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).