研究人员重访了Valiant最初于1984年提出的可学性模型，该模型与更常见的PAC学习模型不同，它允许学习者发出成员查询，并要求假设没有假阳性。他们为Valiant模型中的可学性建立了一个新的表征，表明其学习能力严格介于PAC学习和无查询变体之间。该研究还提出了在Valiant框架内学习$d$维半空间的第一个算法，证明了它们具有可查询性。 AI
影响 深化了对可学性的理论理解，可能影响未来的算法设计。
排序理由 详细介绍理论计算机科学研究的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
Valiant's 1984 paper is widely credited with introducing the PAC learning model, but it, in fact, introduced a different model: unlike PAC learning, the learner receives only positives, may issue membership queries, and must output a hypothesis with no false positives. Prior work…
arXiv:2605.13840v1 Announce Type: new Abstract: Valiant's 1984 paper is widely credited with introducing the PAC learning model, but it, in fact, introduced a different model: unlike PAC learning, the learner receives only positives, may issue membership queries, and must output …