English(EN) Parameter-Free Dynamic Regret for Online Convex Optimization under Heavy-Tailed Noise

新算法HT-PAder解决了重尾噪声下的在线凸优化问题

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-30 04:00

研究人员开发了HT-PAder，这是一种新颖的参数无关算法，旨在解决非平稳环境中具有重尾噪声的在线凸优化挑战。这种新方法结合了带重启的AdaGrad专家和一种无需对元损失进行矩条件约束的路径元算法AdaGrad-Hedge。HT-PAder实现了接近最优的通用动态遗憾，即使在有限方差噪声的情况下也优于先前的方法，并且无需预先了解问题参数。 AI

影响为机器学习中常见的优化问题引入了一种新的算法方法。

排序理由详细介绍在线凸优化新算法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍在线凸优化新算法的学术论文。[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: 70 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 [1]

arXiv cs.LG TIER_1 English(EN) · Vaneet Aggarwal · 2026-07-30 04:00

参数无关的重尾噪声下在线凸优化的动态遗憾

arXiv:2607.27073v1 Announce Type: new Abstract: We study online convex optimization (OCO) in non-stationary environments under heavy-tailed noise, where the stochastic gradient oracle admits only a finite $p$-th central moment for some $p \in (1, 2]$. While static regret is well-…

本文如何被排名

报道来源 [1]

参数无关的重尾噪声下在线凸优化的动态遗憾

相关实体

相关话题