Metraipolis › archive › dc_8c7bd63fbecd
Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime — arXiv:2610.06213
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06213
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:31:30.623Z
- SHA-256 of the archived text
048bc5a9bcb71ad453e406e7facc041591f485ce5e56a2d604ab731c98b67783- Stable URL of this page
https://metraipolis.com/documento/dc_8c7bd63fbecd
How to cite
Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime — arXiv:2610.06213 — arXiv, https://arxiv.org/abs/2610.06213 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8c7bd63fbecd (Metraipolis archive dc_8c7bd63fbecd, sha256 048bc5a9bcb71ad453e406e7facc041591f485ce5e56a2d604ab731c98b67783)
BibTeX
@misc{dc8c7bd63fbecd,
title = {Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime — arXiv:2610.06213},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06213},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8c7bd63fbecd; sha256 048bc5a9bcb71ad453e406e7facc041591f485ce5e56a2d604ab731c98b67783},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06213. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the sampling allocation of LinUCB in the small-gap regime, where the reward gaps are of order at most $n^{-1/2}$ over the decision horizon $n$. This scaling captures the hard instances underlying worst-case regret lower bounds, for which LinUCB is known to be near optimal up to logarithmic factors in $n$. Using a mean-field perspective, we characterize this allocation through the empirical sampling distribution, a macroscopic object that averages the effect of adaptive decisions over the horizon, and identify its limit as $n\to\infty$. We establish that in this regime, the empirical sampling distribution induced by LinUCB converges to the set of D-optimal designs. This central result reveals that, in the small-gap regime, LinUCB not only achieves near optimal minimax regret but also allocates samples in a way that is asymptotically efficient for learning the reward parameter, thereby connecting regret-driven online learning with information-efficient experimental design. Building on the optimal design limit, we obtain two useful consequences. First, we refine the asymptotic regret analysis of LinUCB in the small-gap regime by characterizing its leading-order constant in the limit. Second, we show that, despite LinUCB's adaptive sampling strategy, the regularized least-squares estimator satisfies a central-limit-type theorem in the small-gap regime, thereby enabling valid statistical inference for the reward parameter.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.06213 — 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 2026-10-06T05:27:05.865Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).