PulseAugur
中
实时 13:21:48
English(EN) Optimal Alternating Regret for Online Learning and Games

专家问题和OCO的极小极大交替遗憾已解决 · 跟踪2个来源

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员已经解决了专家问题和在线凸优化（OCO）的极小极大遗憾率问题。对于d专家问题，极小极大交替遗憾被证明是 $\Theta(\log d)$，独立于时间跨度T。这比Hait等人建立的 $\mathcal{O}(T^{1/3}\log^{2/3} d)$ 等先前界限有了显著改进。对于d维紧凸集上的通用OCO，极小极大交替遗憾是 $\Theta(d\log(1+T/d))$，也比先前结果有了实质性改进。这些发现是通过对Hedge等现有算法进行新颖的修正变体实现的，并精心设计了修正项来处理不利的曲率。 AI

影响 为在线学习算法建立了新的理论界限，可能影响博弈论和强化学习的未来研究。

排序理由 在arXiv上发表了两篇学术论文，提出了在线学习和博弈论方面的新颖理论结果。

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

专家问题和OCO的极小极大交替遗憾已解决 · 跟踪2个来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
在arXiv上发表了两篇学术论文，提出了在线学习和博弈论方面的新颖理论结果。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
47 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv stat.ML TIER_1 English(EN) · Mengxiao Zhang ·

    Minimax Alternating Regret for the Experts Problem and Online Convex Optimization

    arXiv:2608.25182v1 Announce Type: new Abstract: In this paper, we study alternating regret in online convex optimization (OCO), motivated by the success of alternating learning dynamics in two-player games. Although previous works have shown that $o(\sqrt{T})$ alternating regret …

  2. arXiv stat.ML TIER_1 English(EN) · Yixin Tao, Weiqiang Zheng ·

    在线学习与博弈的最优交替遗憾

    arXiv:2608.24731v1 Announce Type: cross Abstract: 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 si…

相关实体

相关话题