Metraipolis › archive › dc_44252fec8ee0
Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift — arXiv:2608.26889
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26889
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T14:23:11.056Z
- SHA-256 of the archived text
57a9f9604583e412a52fa246cce7d3fdce94fcea50a1cc4fed44d06167529801- Stable URL of this page
https://metraipolis.com/documento/dc_44252fec8ee0
How to cite
Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift — arXiv:2608.26889 — arXiv (en), https://arxiv.org/abs/2608.26889 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44252fec8ee0 (Metraipolis archive dc_44252fec8ee0, sha256 57a9f9604583e412a52fa246cce7d3fdce94fcea50a1cc4fed44d06167529801)
BibTeX
@misc{dc44252fec8ee0,
title = {Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift — arXiv:2608.26889},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26889},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44252fec8ee0; sha256 57a9f9604583e412a52fa246cce7d3fdce94fcea50a1cc4fed44d06167529801},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26889. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learning-augmented algorithms improve online decisions using predictions, but unreliable advice may harm efficiency and fairness. We study an online allocation problem with finite candidate sets, irreversible decisions, and exposure constraints. We propose a robust and fair rule combining advice with a conservative fallback and fairness correction. Under bounded-error assumptions, we prove consistency and robustness with loss proportional to prediction error. Experiments show stability under adversarial advice and significant reductions in exposure disparity. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.26889 — 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 2026-10-17T13:16:53.530Z 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).