Metraipolis › archive › dc_da45e6d08110

Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and Applications — arXiv:2609.07254

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07254
License (as archived)
CC0-1.0
Archived
2026-10-16T14:29:38.359Z
SHA-256 of the archived text
f978064007d4c7cd94e78d3927d87cbe978a7f1df202d79d355cfa4829cabe7c
Stable URL of this page
https://metraipolis.com/documento/dc_da45e6d08110

How to cite

Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and Applications — arXiv:2609.07254 — arXiv (en), https://arxiv.org/abs/2609.07254 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da45e6d08110 (Metraipolis archive dc_da45e6d08110, sha256 f978064007d4c7cd94e78d3927d87cbe978a7f1df202d79d355cfa4829cabe7c)
BibTeX
@misc{dcda45e6d08110,
  title = {Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and Applications — arXiv:2609.07254},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07254},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da45e6d08110; sha256 f978064007d4c7cd94e78d3927d87cbe978a7f1df202d79d355cfa4829cabe7c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07254. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mathematical programming provides a common language for many decisions embedded in modern machine-learning (ML) and artificial-intelligence (AI) systems: selecting retrieval context, routing tokens, allocating inference compute, fitting structured predictors, protecting against distribution shift, and balancing competing objectives. However, the relevant literature is fragmented across optimization, information retrieval, recommendation, natural-language processing, computer vision, and learning theory. This paper organizes various applications under common mathematical programming paradigms: linear, quadratic, binary and mixed-integer, conic, bilevel, multi-objective, inverse, distributionally robust, submodular, and min--max optimization. We normalize the models with a mostly unified notation and, for every application, identify inputs, decision variables, a principal formulation, structural properties, solution strategies, and limitations. Across paradigms, we compare tractability, relaxation quality, decomposition, approximation guarantees, and scalability bottlenecks. The paper shows that mathematical programming is most useful not as a claim that all learning is LP or MIP, but as a disciplined interface between predictions and constrained decisions.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-09 in math.OC).
Categorie arXiv: Optimization and Control (math.OC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.07254 — 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 2026-10-16T14:09:21.686Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).