通过$\gamma$-VC维提升简单弱学习器的表达能力
Boosting and the Expressive Power of Simple Weak Learners via the $γ$-VC Dimension
浏览论文内容
中文总结 AI 辅助
本文通过$\gamma$-VC维研究提升算法中弱学习器的表达能力,证明该参数以常数因子刻画弱到强学习的样本复杂度,并改进经典VC维与$\gamma$-VC维的关系,给出决策桩和轴平行矩形的改进上下界。
中文摘要 AI 辅助
提升(Boosting)将相对于随机猜测具有小优势的弱假设转化为高精度的预测器,但所得分类器的表达能力可能强烈依赖于基类的结构。我们通过Alon等人(STOC 2021)引入的$\gamma$-VC维来研究这一现象。我们的第一个结果表明,该参数刻画了从弱到强学习的样本复杂度,其缩放因子在$\gamma$中为常数。然后,我们锐化了经典VC维与$\gamma$-VC维之间的一般关系。最后,我们还给出了$\mathbb{R}^d$中决策桩和轴平行矩形这两个基本概念类的$\gamma$-VC维的改进上下界。
英文摘要
Boosting converts weak hypotheses with a small edge over random guessing into highly accurate predictors, but the expressive power of the resulting classifier can depend strongly on the structure of the base class. We study this phenomenon through the $γ$-VC dimension introduced by Alon et al. (STOC 2021). Our first result shows that this parameter characterizes the sample complexity for weak-to-strong learning up to a constant factor scaling in $γ$. We then sharpen the general relationship between the classic VC dimension and the $γ$-VC dimension. Finally, we also give improved upper and lower bounds on the $γ$-VC dimension for the fundamental concept classes of decision stumps and axis-parallel rectangles in $\mathbb{R}^d$.
发表机构
- Aarhus University(奥胡斯大学)
机构由 AI 辅助整理,请以论文原文为准。