一种最优的不可知PAC算法
An Optimal Agnostic PAC Algorithm
浏览论文内容
中文总结 AI 辅助
该研究针对有限VC维的二元分类函数类,构造出达到统计最优风险界的不可知PAC学习算法,确定了其样本复杂度(仅差通用常数),匹配了已有下界。
中文摘要 AI 辅助
设$H\subseteq\{-1,+1\}^X$是VC维$d\ge1$的有限类,记$L$为二元风险,$L^*=\min_{h\in H}L(h)$,我们构造了一个学习器,其统计最优风险界为:从大小为$n$的独立同分布样本出发,对任意$0<\delta\le1/2$,以至少$1-\delta$的概率,满足$L(\widehat h) \le L^*+ 7\cdot10^8\left( \sqrt{\frac{L^*(d+\log(1/\delta))}{n}} +\frac{d+\log(1/\delta)}{n} \right)$。这在每个固定$L^*$下,确定了不可知PAC学习的样本复杂度(仅差通用常数),与Devroye、Györfi和Lugosi的《模式识别的概率理论》(Springer,1996)中的下界相匹配。
英文摘要
Let $H\subseteq\{-1,+1\}^X$ be a class of finite VC dimension $d\ge1$. Writing $L$ for the binary risk and $L^*=\min_{h\in H}L(h)$, we construct a learner achieving the statistically optimal risk bound: from an i.i.d.\ sample of size $n$, for every $0<δ\le 1/2$, with probability at least $1-δ$, \[ L(\widehat h) \le L^*+ 7\cdot10^8\left( \sqrt{\frac{L^*(d+\log(1/δ))}{n}} +\frac{d+\log(1/δ)}{n} \right). \] This settles the sample complexity of agnostic PAC learning up to universal constants at every fixed $L^*$, matching the lower bounds of Devroye, Györfi, and Lugosi [A Probabilistic Theory of Pattern Recognition, Springer, 1996].
发表机构
- Aarhus University(奥胡斯大学)
- The University of Hong Kong(香港大学)
- University of California, Berkeley(加州大学伯克利分校)
机构由 AI 辅助整理,请以论文原文为准。