Metraipolis › archive › dc_c8aae5a9976f

Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints — arXiv:2608.16375

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16375
License (as archived)
CC0-1.0
Archived
2026-10-18T18:07:11.678Z
SHA-256 of the archived text
5d6aedd0a7670747d669510d27b0e3a68688dc723f71e0fceb43e7c2bfbd7e35
Stable URL of this page
https://metraipolis.com/documento/dc_c8aae5a9976f

How to cite

Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints — arXiv:2608.16375 — arXiv (en), https://arxiv.org/abs/2608.16375 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8aae5a9976f (Metraipolis archive dc_c8aae5a9976f, sha256 5d6aedd0a7670747d669510d27b0e3a68688dc723f71e0fceb43e7c2bfbd7e35)
BibTeX
@misc{dcc8aae5a9976f,
  title = {Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints — arXiv:2608.16375},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16375},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8aae5a9976f; sha256 5d6aedd0a7670747d669510d27b0e3a68688dc723f71e0fceb43e7c2bfbd7e35},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16375. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study online routing to subsets of experts under aggregate bandit feedback and long-run operational constraints. Expert contributions can be complementary: for each task dimension, the best selected expert determines the contribution, and the total reward aggregates these dimension-wise maxima. At the same time, capacity, budget, and fairness requirements impose lower and upper bounds on long-run expert activation frequencies. A fixed deterministic subset cannot generally satisfy such heterogeneous requirements, motivating a stochastic routing policy. We formalize this problem as Multinomial Subset Routing (MSR). The learner maintains a distribution \(q\) over \(K\) experts, samples an expert independently \(M\) times from \(q\), and routes each task to the distinct sampled experts. We propose OMD-Approachability, which combines online mirror descent with Blackwell's approachability to optimize MSR under two-sided operational constraints. We establish \(O(T^{-1/2})\) average reward regret and expected constraint violation. We also quantify the approximation gap induced by a linear surrogate, and evaluate the approach on a real-world crowdsourcing dataset.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16375 — 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 2026-10-18T16:29:14.111Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).