Metraipolis › archive › dc_75896d72302b
Corruption-Robust Sparse Linear Contextual Bandits with Knapsack Constraints — arXiv:2609.37189
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37189
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:30:41.468Z
- SHA-256 of the archived text
5ad70b1a504ff807c5c473098ea71951661e3a657c274356a3899a426d856786- Stable URL of this page
https://metraipolis.com/documento/dc_75896d72302b
How to cite
Corruption-Robust Sparse Linear Contextual Bandits with Knapsack Constraints — arXiv:2609.37189 — arXiv (en), https://arxiv.org/abs/2609.37189 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75896d72302b (Metraipolis archive dc_75896d72302b, sha256 5ad70b1a504ff807c5c473098ea71951661e3a657c274356a3899a426d856786)
BibTeX
@misc{dc75896d72302b,
title = {Corruption-Robust Sparse Linear Contextual Bandits with Knapsack Constraints — arXiv:2609.37189},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37189},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75896d72302b; sha256 5ad70b1a504ff807c5c473098ea71951661e3a657c274356a3899a426d856786},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37189. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study sparse linear contextual bandits with knapsack constraints under joint reward and consumption corruption. Consumption corruption creates a challenge beyond corrupted rewards: it affects not only statistical estimates, but also the recorded budget, resource prices, and stopping decisions that govern future allocation. We develop Robust Optimistic Primal--Dual (ROPD), an estimator-modular framework that combines corruption-aware confidence widths with online resource prices and a budget-safety rule. With concrete sparse implementation, ROPD achieves regret against a clean population-LP benchmark of $\widetilde O(T^{2/3}+\Gamma T^{1/3})$ under forced exploration and population-design coverage, and $\widetilde O(\sqrt T+\Gamma)$ under on-policy realized-design coverage, for a supplied valid corruption bound $\Gamma$ under the stated proportional-budget scaling and fixed model/design parameters. When the corruption level is unknown, Shared-Grid adapts confidence radii around common point estimates fitted to a single realized history, incurring explicit initialization and master-comparison costs; its sharper on-policy guarantee additionally requires recommendation coverage. Both methods preserve observed budgets on every realization and bound clean resource violation by cumulative consumption corruption. These results connect corruption-robust sparse estimation with resource accounting, pricing, and stopping in high-dimensional online allocation.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.37189 — 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 2026-10-07T16:59:48.300Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).