返回主题:线性模型与优化算法

知识卡片

普通读书笔记卡 · 3710.d.2.a.1

完美专家使多数淘汰错误至多对数

理解等级:高级

若n位专家中至少一位始终正确,只保留从未出错者并按其多数票预测。学习者每次预测错误,至少淘汰当前一半专家;完美专家始终留下,因此最多错⌈lg n⌉次。

这张卡片看不懂?

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

      Lemma 33.3 Suppose that out of n experts, there is one who always makes the correct prediction for all T events. Then there is an algorithm that makes at most ⌈1g n⌉ mistakes. Proof The algorithm maintains a set S consisting of experts who have not yet made a mistake. Initially, S contains all n experts. The algorithm’s prediction is always the majority vote of the predictions of the experts remaining in set S.

    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:Lemma 33.3 Suppose that out of n experts, there is one who always makes the correct prediction for all T events. Then there is an algorithm that makes at most ⌈ 1g n ⌉ mistakes. Proof The algorithm maintains a set S consisting of experts who have not yet made a mistake. Initially, S contains all n experts. The algorithm’s prediction is always the majority vote of the predictions of the experts remaining in set S .