English(EN) $\tilde{O}(\sqrt{T})$ Regret and Polylogarithmic Constraint Violation for COCO

新算法将人工智能优化约束违反降至多对数级别

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员开发了一种新的约束在线凸优化算法，该算法可将累积约束违反 (CCV) 显著降低至多对数级别，同时保持近乎最优的遗憾。该方法将连续 Hedge 与收缩可行集上的消除相结合，并利用 Grünbaum 不等式来约束 CCV。当成本函数是指数凹函数或强凸函数时，该算法可实现对数遗憾。 AI

影响这项研究通过最大限度地减少复杂优化任务中的约束违反，有望带来更高效、更可靠的人工智能系统。

排序理由该集群包含一篇详细介绍特定机器学习问题新算法的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 10 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍特定机器学习问题新算法的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Dhruv Sarkar, Abhishek Sinha · 2026-10-27 04:00

$\tilde{O}(\sqrt{T})$ 遗憾与COCO的多对数约束违反

arXiv:2610.03983v2 Announce Type: replace Abstract: We study constrained online convex optimization with adversarial convex costs and constraints ($\mathsf{COCO}$). At each round $t\in[T]$, a learner selects $x_t$ from a $d$-dimensional convex decision set $X$, after which an ada…