English(EN) Smoothed Analysis of Learning from Positive Samples

平滑分析使仅正样本学习成为可能

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-13 04:00

研究人员开发了一种用于仅正样本学习的平滑分析方法，这是二元分类中的一个挑战性问题。与学习几乎不可能的最坏情况场景不同，这种新方法表明，在平滑条件下，所有 VC 类都可学习。该工作还为参数估计、截断检测和从参考分布学习中的相关问题引入了高效算法。 AI

影响引入了一个理论框架，可能使生物信息学和生态学等领域的从不完整数据集中学习成为可能。

排序理由该集群包含一篇详细介绍机器学习问题新理论方法的学术论文。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍机器学习问题新理论方法的学术论文。[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: 120 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。

arXiv stat.ML TIER_1 English(EN) · Jane H. Lee, Anay Mehrotra, Manolis Zampetakis · 2026-05-13 04:00

Smoothed Analysis of Learning from Positive Samples

arXiv:2504.10428v2 Announce Type: replace Abstract: Binary classification from positive-only samples is a variant of PAC learning where the learner receives i.i.d. positive samples and aims to learn a classifier with low error. Previous work by Natarajan, Gereb-Graus, and Shvayts…