Metraipolis › archive › dc_e18d680c032e

Local Violation Certification for Linear Predict-Then-Optimize Pipelines — arXiv:2608.04474

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.04474
License (as archived): CC0-1.0
Archived: 2026-10-31T11:34:50.349Z
SHA-256 of the archived text: 201bda8c23e5d1aeadc3fa7668d2f47a10f5474d63a4e89508c6e75bf713d81c
Stable URL of this page: https://metraipolis.com/documento/dc_e18d680c032e

How to cite

Local Violation Certification for Linear Predict-Then-Optimize Pipelines — arXiv:2608.04474 — arXiv (en), https://arxiv.org/abs/2608.04474 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e18d680c032e (Metraipolis archive dc_e18d680c032e, sha256 201bda8c23e5d1aeadc3fa7668d2f47a10f5474d63a4e89508c6e75bf713d81c)

BibTeX

@misc{dce18d680c032e,
  title = {Local Violation Certification for Linear Predict-Then-Optimize Pipelines — arXiv:2608.04474},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04474},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e18d680c032e; sha256 201bda8c23e5d1aeadc3fa7668d2f47a10f5474d63a4e89508c6e75bf713d81c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04474. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Data-driven decision pipelines combining predictive machine learning models with downstream optimization software are increasingly used to make high-stakes operational decisions. Certifying the safety, fairness, and reliability of these decisions is essential, yet traditional scenario generation methods rely on repeated random testing, which becomes computationally prohibitive when failure events are rare and offers little insight into why failures occur. We present a framework for local violation certification designed specifically for linear decision pipelines under input uncertainty. We mathematically demonstrate that standard sampling methods fail efficiently for rare violations, motivating a direct structural approach. By analyzing the fixed decision boundary of a deployed pipeline, we show that the local risk of failure can be calculated directly in closed form using a single optimization solve. Furthermore, we introduce an exact sampling procedure and closed-form risk statistics that provide feature-level attributions (identifying which input characteristics contribute most to potential non-compliance) without requiring repetitive random trials or complex sampling algorithms. We demonstrate our approach on an economic power dispatch system subject to emissions regulations, delivering precise, auditable risk assessments at a fraction of the traditional computational cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.04474 — 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 2026-10-31T11:24:48.784Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).