← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 8856.c · 生成模型:GPT-6

演化策略以扰动估计搜索方向

理解等级:高级

演化策略随机采样εᵢ,比较J(θ+σεᵢ),再根据损失加权组合扰动方向。原书示例估计量为(1/σM)ΣJ(θ+σεᵢ)εᵢ,对其作下降更新,不需要原函数解析梯度。它通常对应平滑目标的随机估计,样本数与扰动尺度共同影响噪声和可跨越范围。

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

      compute it by sampling perturbations of θ, and seeing which perturbation leads to lower loss. In this strategy, we evaluate J(θ + ϵ) for a set of perturbations ϵ, then move toward the ϵ's that decreased the loss. Approaches of this kind are sometimes called evolution strategies [47, 421], and a basic version of this algorithm is given in algorithm 10.4.

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第10章《基于梯度的学习算法》(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/c010.xhtml) - 结论依据:摘录中关于演化策略以扰动估计搜索方向的定义、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:compute it by sampling perturbations of θ, and seeing which perturbation leads to lower loss. In this strategy, we evaluate J(θ + ϵ) for a set of perturbations ϵ, then move toward the ϵ's that decreased the loss. Approaches of this kind are sometimes called evolution strategies [47, 421], and a basic version of this algorithm is given in algorithm 10.4.