一篇新的研究论文通过PAC学习的视角，重点关注组合函数树，探讨了科学发现的样本复杂度。该研究证明了泛化量Rademacher复杂度受限于树的深度及其算子的Lipschitz常数，而不是指数增长。作者开发了一个可训练可微算子树的代码库，并通过实证证明泛化差距与其预测复杂度相关。 AI
影响 为符号回归和组合函数学习提供了理论基础，有望提升AI进行科学发现的能力。
排序理由 该集群包含一篇阐述机器学习理论研究的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.29331v1 Announce Type: cross Abstract: Scientific discovery via symbolic regression is often viewed as statistically and computationally intractable because the hypothesis space of expressions grows combinatorially with depth. This paper revisits the statistical side t…
Scientific discovery via symbolic regression is often viewed as statistically and computationally intractable because the hypothesis space of expressions grows combinatorially with depth. This paper revisits the statistical side through the lens of PAC learning, focusing on compo…