Metraipolis › archive › dc_2b16489eda09
Strongly Adaptive Online Learning Achieves Uniform Discounted Regret — arXiv:2610.39292
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39292
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:25:02.532Z
- SHA-256 of the archived text
49e5e3ab1f11772df1aeb0a42f2e3f105e9e26e5b449ad7fee3c207336c95e56- Stable URL of this page
https://metraipolis.com/documento/dc_2b16489eda09
How to cite
Strongly Adaptive Online Learning Achieves Uniform Discounted Regret — arXiv:2610.39292 — arXiv (en), https://arxiv.org/abs/2610.39292 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b16489eda09 (Metraipolis archive dc_2b16489eda09, sha256 49e5e3ab1f11772df1aeb0a42f2e3f105e9e26e5b449ad7fee3c207336c95e56)
BibTeX
@misc{dc2b16489eda09,
title = {Strongly Adaptive Online Learning Achieves Uniform Discounted Regret — arXiv:2610.39292},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39292},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b16489eda09; sha256 49e5e3ab1f11772df1aeb0a42f2e3f105e9e26e5b449ad7fee3c207336c95e56},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39292. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Discounted regret measures the performance of an online learner by assigning exponentially decaying weights to past losses, reflecting the greater importance of recent losses in non-stationary online learning. While previous work obtains uniform discounted regret bounds over a continuous range of discount factors using a specialized meta-algorithm, its results are limited to convex functions. In this paper, we demonstrate that strongly adaptive regret bounds can directly imply uniform discounted regret guarantees for convex, strongly convex, and exp-concave loss functions. Our key observation is that discounted regret against a fixed comparator admits an exact decomposition into a convex combination of interval regrets. For convex functions, this reduction yields an $O(\sqrt{\log T/(1-\lambda)})$ discounted regret bound for all discount factors $\lambda\in(0,1)$, matching the previous rate over a broader range of discount factors. For strongly convex and exp-concave functions, we provide regret bounds of $O\left(\log T\left(1+\log\frac{1}{1-\lambda}\right)\right)$.
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/2610.39292 — 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 2026-11-01T02:12:44.159Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).