Metraipolis › archive › dc_e1cb8a7339cc

CG4AI: A Column Generation Framework for Training AI Models Under Constraints — arXiv:2608.26375

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.26375
License (as archived): CC0-1.0
Archived: 2026-10-17T14:24:59.786Z
SHA-256 of the archived text: 30669fa6d08388420060d96076aba5cd4c2b2a50003708c098d255c562214d58
Stable URL of this page: https://metraipolis.com/documento/dc_e1cb8a7339cc

How to cite

CG4AI: A Column Generation Framework for Training AI Models Under Constraints — arXiv:2608.26375 — arXiv (en), https://arxiv.org/abs/2608.26375 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1cb8a7339cc (Metraipolis archive dc_e1cb8a7339cc, sha256 30669fa6d08388420060d96076aba5cd4c2b2a50003708c098d255c562214d58)

BibTeX

@misc{dce1cb8a7339cc,
  title = {CG4AI: A Column Generation Framework for Training AI Models Under Constraints — arXiv:2608.26375},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26375},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1cb8a7339cc; sha256 30669fa6d08388420060d96076aba5cd4c2b2a50003708c098d255c562214d58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26375. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Standard machine-learning training minimizes a loss function over a dataset, but does not guarantee that the resulting model will satisfy predefined rules or constraints on its outputs. In many real-world applications, ranging from autonomous systems to network routing, such guarantees are essential. We propose CG4AI, a framework that builds a convex combination of AI models while enforcing linear constraints on the combined output. A master linear program (LP) determines the optimal mixture weights, while a pricing subproblem generates new models guided by LP dual variables, focusing attention on the most violated constraints. A cutting-plane procedure extends feasibility guarantees beyond the training set. We apply CG4AI to two problems: (i) digit classification on MNIST, where we demonstrate four distinct uses of constraints, learning from constraints alone, improving adversarial robustness, correcting misclassified examples, and enforcing output relabeling; and (ii) the multi-commodity flow problem, where link capacity constraints are enforced on neural-network routing predictors. Experiments on MNIST and standard SNDLIB benchmark networks show that CG4AI reliably produces feasible predictors while achieving better accuracy than single-model baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Discrete Mathematics (cs.DM).
Pagina del lavoro: https://arxiv.org/abs/2608.26375 — 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 2026-10-17T13:16:53.632Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).