Metraipolis › archive › dc_d8cc29c8d7dd

Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization — arXiv:2608.04149

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04149
License (as archived)
CC0-1.0
Archived
2026-10-31T11:26:19.713Z
SHA-256 of the archived text
3043b9c24377527026614f420ecfe963e169d6dab1c67776001b01fee27e449c
Stable URL of this page
https://metraipolis.com/documento/dc_d8cc29c8d7dd

How to cite

Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization — arXiv:2608.04149 — arXiv (en), https://arxiv.org/abs/2608.04149 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8cc29c8d7dd (Metraipolis archive dc_d8cc29c8d7dd, sha256 3043b9c24377527026614f420ecfe963e169d6dab1c67776001b01fee27e449c)
BibTeX
@misc{dcd8cc29c8d7dd,
  title = {Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization — arXiv:2608.04149},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04149},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8cc29c8d7dd; sha256 3043b9c24377527026614f420ecfe963e169d6dab1c67776001b01fee27e449c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04149. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Swap regret governs the rate at which uncoupled learning dynamics converge to correlated equilibria in multiplayer general-sum games. Under full-information feedback, the best previous guarantee when every player follows the same dynamics grows logarithmically in the horizon $T$. We construct uncoupled dynamics under which every player incurs only $O(nm^2\sqrt{\log m\log T})$ swap regret, where $n$ is the number of players and $m$ bounds the number of actions per player. To our knowledge, this is the first sublogarithmic individual guarantee in this setting, and it implies that the time-averaged product distribution of play is an $O(nm^2\sqrt{\log m\log T}/T)$-approximate correlated equilibrium. The key algorithmic choice is to combine the Blum--Mansour reduction with optimistic follow-the-regularized-leader using a hybrid regularizer that separately weights negative Shannon entropy and the log-barrier: the entropy controls the optimistic prediction error, whereas the log-barrier controls the transition-matrix movement through its Bregman divergence. A new sensitivity theorem for stationary distributions of Markov chains, which involves neither mixing parameters nor the smallest transition probability, transfers this control to the played strategies and yields a simpler analysis without local-norm or self-concordance arguments. The guarantee is preserved by an adversarially robust variant that additionally ensures $O(nm^2\sqrt{\log m\log T}+\sqrt{mT\log m})$ swap regret against arbitrary utility sequences, and by a horizon-free variant that requires no prior knowledge of $T$.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-08-06 in cs.GT).
Categorie arXiv: Computer Science and Game Theory (cs.GT) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.04149 — 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 2026-10-31T11:15:42.973Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).