Metraipolis › archive › dc_ebd4deac4204
Linear Bandits under Exact Sliding-Window Constraints — arXiv:2610.08745
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08745
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:42:00.182Z
- SHA-256 of the archived text
02014d66af7d572929abadd7cc1f812bfd740c8a4a630e43b22ae86cce066e1f- Stable URL of this page
https://metraipolis.com/documento/dc_ebd4deac4204
How to cite
Linear Bandits under Exact Sliding-Window Constraints — arXiv:2610.08745 — arXiv (en), https://arxiv.org/abs/2610.08745 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebd4deac4204 (Metraipolis archive dc_ebd4deac4204, sha256 02014d66af7d572929abadd7cc1f812bfd740c8a4a630e43b22ae86cce066e1f)
BibTeX
@misc{dcebd4deac4204,
title = {Linear Bandits under Exact Sliding-Window Constraints — arXiv:2610.08745},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08745},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebd4deac4204; sha256 02014d66af7d572929abadd7cc1f812bfd740c8a4a630e43b22ae86cce066e1f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08745. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study linear bandits under exact sliding-window constraints, where every consecutive block of actions must belong to a prescribed feasible set. In the offline setting, where the reward function is known, we show that convexity and cyclic-shift invariance make a stationary solution optimal when $w\mid T$ and within an additive $O(w)$ gap otherwise. In the online setting, we show that geometric structure alone is insufficient for learning, and sublinear regret can be impossible. We introduce a transition diameter $\tau$ that quantifies feasible reachability and develop a rare-switching OFUL algorithm with regret $\widetilde{O}(d\sqrt{T}+\tau d+w)$ against the offline-optimal feasible trajectory. Finally, we remove cyclic invariance and consider general sliding-window constraints, where optimal behavior may be non-stationary. We represent recent action history as the state of a finite-memory control problem and introduce a history-state diameter $D$ that measures feasible communication between viable histories. Combining optimistic remaining-horizon planning with rare policy updates, we obtain a regret bound of $\widetilde{O}(d\sqrt{T}+dD+w)$. We evaluate our approach on real-world and synthetic benchmarks, showing that it maintains exact feasibility while achieving reward and regret comparable to baselines with substantially fewer policy updates.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.08745 — 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 2026-10-07T11:19:24.851Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).