Metraipolis › archive › dc_7a870270ea25
Optimal Alternating Regret for Online Learning and Games — arXiv:2608.24731
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.24731
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:36:24.025Z
- SHA-256 of the archived text
e2e114863fda622dc02566f33b9c83c28824844b15811d116a643ec1e512c635- Stable URL of this page
https://metraipolis.com/documento/dc_7a870270ea25
How to cite
Optimal Alternating Regret for Online Learning and Games — arXiv:2608.24731 — arXiv (en), https://arxiv.org/abs/2608.24731 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a870270ea25 (Metraipolis archive dc_7a870270ea25, sha256 e2e114863fda622dc02566f33b9c83c28824844b15811d116a643ec1e512c635)
BibTeX
@misc{dc7a870270ea25,
title = {Optimal Alternating Regret for Online Learning and Games — arXiv:2608.24731},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.24731},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a870270ea25; sha256 e2e114863fda622dc02566f33b9c83c28824844b15811d116a643ec1e512c635},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24731. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We settle the minimax-optimal alternating regret, a regret notion motivated by alternating learning dynamics in games, for both online linear optimization (OLO) and online convex optimization (OCO). For OLO over the probability simplex $\Delta_d$, we give an algorithm with $O(\log d)$ alternating regret that remains a constant for any time horizon $T$, and a matching lower bound. Our constant regret bound significantly improves previous results with $O(\log ^{2/3}d \cdot T^{1/3})$ regret [Cevher, Cutkosky, Kavis, Piliouras, Skoulakis, Viano, NeurIPS 2023, Hait, Li, Luo, Zhang, COLT 2025]. As a result, we obtain alternating learning dynamics with $O(\log d /T)$ convergence to Nash equilibria in two-player zero-sum games and $O(\log d /T)$ convergence to coarse correlated equilibria in two-player general-sum games. This is the first uncoupled learning dynamics with $O(1/T)$ convergence to CCE in two-player general-sum games, while all prior works suffer additional $\log T$ factors. For general OCO over a $d$-dimensional compact convex set, we give an algorithm with $O(d\log (1+T/d))$ alternating regret, improving the previous best of $\widetilde{O}(d^{2/3}T^{1/3})$. We also prove a matching lower bound of $\Omega(d\log (1+T/d))$, showing that the $\Omega(\log T)$ factor is unavoidable.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Science and Game Theory (cs.GT); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.24731 — 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 2026-10-18T06:28:52.278Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).