arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Machine Learning · 会议 · Machine Learning

2026-04-20 至 2026-04-20 共收录 2
2604.16087 2026-04-20 cs.LG stat.ML

The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback

更艰难的道路:零和博弈中无耦合学习的最后迭代收敛

Côme Fiegel, Pierre Ménard, Tadashi Kozuno, Michal Valko, Vianney Perchet

机构 * Inria - FairPlay(Inria-公平游戏实验室) Stealth AI Startup / Inria / ENS(隐形AI初创公司 / Inria / 索邦大学) Criteo AI Lab, Paris, France(Criteo AI实验室,巴黎,法国)

AI总结 研究零和矩阵博弈在重复玩和带隙反馈下的学习问题,提出无耦合算法保证在无通信情况下最后迭代收敛到纳什均衡,发现收敛至纳什均衡对性能不利,最佳速率为Ω(T^{-1/4}),优于常规的Ω(T^{-1/2})。

Comments Accepted at the 42nd International Conference on Machine Learning (ICML 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.09355 2026-04-20 cs.GT cs.AI cs.LG

Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All

价格、出价、价值:一种由机器学习驱动的综合拍卖以统御它们所有

Ermis Soumalias, Jakob Heiss, Jakob Weissteiner, Sven Seuken

机构 * Department of Informatics, University of Zurich, Zurich, Switzerland(苏黎世大学信息学院) ETH AI Center, Zurich, Switzerland(苏黎世联邦理工学院AI中心) Department of Mathematics, ETH Zurich, Zurich, Switzerland(苏黎世联邦理工学院数学系) Department of Statistics, University of California, Berkeley, USA(加州大学伯克利分校统计系)

AI总结 本文提出一种基于机器学习的综合拍卖,通过结合价值和需求查询提升效率,减少查询次数并降低投标人认知负担,建立新的实践和效率基准。

Comments ICML 2025 (Oral Presentation) 8 pages + appendix

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56570-56614, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏