PulseAugur
实时 19:27:40
English(EN) Actively Learning Halfspaces without Synthetic Data

新算法无需合成数据即可学习半空间

研究人员开发了一种新的算法,可以在不依赖合成数据的情况下学习半空间,解决了计算几何学中一个长期存在的挑战。该算法在从大小为 D 的集合中学习具有法向量的半空间时,实现了 $\Theta(D + \log n)$ 的紧密界限。这种方法还为 PAC 学习产生了近乎最优的算法,即使存在对抗性破坏,也需要 $O(\min(D + \log(1/\varepsilon), 1/\varepsilon) \cdot \log D)$ 次查询即可在误差 $\varepsilon$ 内学习一个函数。 AI

排序理由 该集群包含一篇学术论文,详细介绍了计算几何学问题的一种新算法。[lever_c_demoted from research: ic=1 ai=0.4]

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 →

新算法无需合成数据即可学习半空间

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
该集群包含一篇学术论文,详细介绍了计算几何学问题的一种新算法。[lever_c_demoted from research: ic=1 ai=0.4]
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
Standard
On-topic for AI-industry coverage; kept in the public index.
Story freshness
59 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]

  1. arXiv cs.LG TIER_1 English(EN) · Hadley Black, Kasper Green Larsen, Arya Mazumdar, Barna Saha, Geelon So ·

    无需合成数据的主动学习半空间

    arXiv:2509.20848v2 Announce Type: replace-cross Abstract: In the classic point location problem, one is given an arbitrary dataset $X \subset \mathbb{R}^d$ of $n$ points with query access to an unknown halfspace $f : \mathbb{R}^d \to \{0,1\}$, and the goal is to learn the label o…