Metraipolis › archive › dc_3d54cbf7c871
Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits — arXiv:2609.28718
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28718
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T05:26:24.738Z
- SHA-256 of the archived text
fa33f8e7288259d4ecaeb3d650e22a13b8989ae3600baf15da72ede9e4d46931- Stable URL of this page
https://metraipolis.com/documento/dc_3d54cbf7c871
How to cite
Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits — arXiv:2609.28718 — arXiv (en), https://arxiv.org/abs/2609.28718 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d54cbf7c871 (Metraipolis archive dc_3d54cbf7c871, sha256 fa33f8e7288259d4ecaeb3d650e22a13b8989ae3600baf15da72ede9e4d46931)
BibTeX
@misc{dc3d54cbf7c871,
title = {Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits — arXiv:2609.28718},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28718},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d54cbf7c871; sha256 fa33f8e7288259d4ecaeb3d650e22a13b8989ae3600baf15da72ede9e4d46931},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28718. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study Bayesian linear bandits with an isotropic Gaussian parameter, independent Gaussian candidate arms, and Gaussian reward noise when the horizon is proportional to the dimension. The normalized posterior uncertainty has an explicit limit that is uniform over all causal policies. Gaussian posterior identities then determine the limiting parameter overlaps without an assumed closure of the adaptive recursion. These results yield exact regret curves for Thompson sampling, posterior-mean greedy selection, and a family of policies that scale the posterior sampling covariance. The normalized realized cumulative regret converges in L1, uniformly on compact proportional-time intervals. A policy-uniform lower bound identifies the limiting optimal Bayes regret and proves that posterior-mean greedy selection attains it. Thompson sampling incurs a strictly larger leading regret; its instantaneous regret ratio relative to greedy selection lies between one and two and approaches two at long proportional horizons. Closed-form cumulative curves also identify a different comparison in the vanishing-noise limit. Finally, the instantaneous regret converges to a nondegenerate Gaussian decision-loss distribution, rather than to its mean. The analysis separates the amount of information acquired by a bandit policy from the quality of the decisions made using that information. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Statistics Theory (math.ST). Pagina del lavoro: https://arxiv.org/abs/2609.28718 — 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 2026-10-08T04:50:39.549Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).