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.1.b

乘性权重可扩展到实值损失

理解等级:中级

乘性权重不局限二元预测:结果和预测可为实数,更新因子可随损失变化,也可把权重归一化成专家抽样分布。

具体保证须按新损失与更新规则重新分析,不能直接套二元错误数界。

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

      Multiplicative weights methods typically refer to a broader class of algorithms that includes WEIGHTED-MAJORITY. The outcomes and predictions need not be only 0 or 1, but can be real numbers, and there can be a loss associated with a particular outcome and prediction. The weights can be updated by a multiplicative factor that depends on the loss, and the algorithm can, given a set of weights, treat them as a distribution on experts and use them to choose an expert to follow in each event. Even in these more general settings, bounds similar to Theorem 33.4

    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[35000,40000))。 - 结论依据:原文第33.2节加权多数算法与势能证明,或第33.3节梯度、步长和局部极小讨论;相关公式图已核对。 - 原始内容:Multiplicative weights methods typically refer to a broader class of algorithms that includes W EIGHTED -M AJORITY . The outcomes and predictions need not be only 0 or 1, but can be real numbers, and there can be a loss associated with a particular outcome and prediction. The weights can be updated by a multiplicative factor that depends on the loss, and the algorithm can, given a set of weights, treat them as a distribution on experts and use them to choose an expert to follow in each event. Even in these more general settings, bounds similar to Theorem 33.4