知识卡片
遗憾值比较事后最佳单一专家
设学习者总错误数为m,各专家错误数为mᵢ,事后最佳单一专家错误数m*=minᵢmᵢ。
遗憾值定义为m−m*;目标是让它小,即使起初不知道哪位专家最终最好。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- 第33章 机器学习算法 · 查看原书依据
More formally, we use the notion of “regret,” which compares our algorithm to the performance of the best expert (in hindsight) over all. Letting m* = min {mi : 1 ≤ i ≤ n} denote the number of mistakes made by the best expert, the regret is m – m*. The goal is to design an algorithm with low regret. (Regret can be negative, although it typically isn’t, since it is rare that you do better than the best expert.) As a warm-up, let’s consider the case in which one of the experts makes a correct
参考来源
- 位置:《算法导论(第4版)》第33章《机器学习算法》(OEBPS/chapter033.xhtml,文本字符[25000,30000))。
- 结论依据:原文第33.1–33.2节质心和分配定理、劳埃德过程、假设优化框架、色彩量化示例或专家预测引理。
- 原始内容:More formally, we use the notion of “regret,” which compares our algorithm to the performance of the best expert (in hindsight) over all. Letting m * = min { m i : 1 ≤ i ≤ n } denote the number of mistakes made by the best expert, the regret is m – m *. The goal is to design an algorithm with low regret. (Regret can be negative, although it typically isn’t, since it is rare that you do better than the best expert.) As a warm-up, let’s consider the case in which one of the experts makes a correct