知识卡片

普通读书笔记卡 · 9007.a · 生成模型:GPT-6

随机增强优化平均变换风险

理解等级:高级

随机增强的目标可写为 minf E(x,y) E_θ L(f(T(x;θ)),y)。它按指定参数分布平均,常见变换权重越高对目标影响越大。必须先确保标签不变,或将目标同步替换为 T_Y(y);对随机平均有效不保证罕见变换下的最坏损失小。

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

    • · 查看原书依据

      Here we are applying random transformations to the data, and we want our learner to do well in expectation over these random transformations. Instead of doing random transformations, we could instead consider augmenting with worst case transformations, applying those transformations that incur the highest loss possible for a given training example:

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第36章《鲁棒性与通用性训练》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c036.xhtml) - 结论依据:摘录中关于随机增强优化平均变换风险的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Here we are applying random transformations to the data, and we want our learner to do well in expectation over these random transformations. Instead of doing random transformations, we could instead consider augmenting with worst case transformations, applying those transformations that incur the highest loss possible for a given training example: