知识卡片

普通读书笔记卡 · 3710.f.2.b

梯度下降返回迭代点均值

理解等级:中级

固定步长γ和迭代数T后,每轮按x⁽ᵗ⁺¹⁾=x⁽ᵗ⁾−γ∇f(x⁽ᵗ⁾)更新;此版本返回前T个迭代点的均值,不返回最后一个点。

平均值是后续误差界所分析的输出。

这张卡片看不懂?

已有反馈 · 0 / 10 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

      The procedure GRADIENT-DESCENT on the facing page takes as input a function f, an initial point x(0) ∈ ℝn, a fixed step-size multiplier γ > 0, and a number T > 0 of steps to take. Each iteration of the for loop of lines 2–4 performs a step by computing the n-dimensional gradient at point x(t) and then moving distance γ in the opposite direction in the n-dimensional space. The complexity of computing the gradient depends on the function f and can sometimes be expensive. Line 3 sums the points visited. After the loop terminates, line 6 returns x-avg, the average of all the points visited except for the last one, x(T). It might seem more natural to return x(T), and in fact, in many circumstances, you might prefer to have the function return x(T). For the version we will analyze, however, we use x-avg. G

    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[45000,50000))。 - 结论依据:原文第33.3节梯度下降、凸性、误差界或约束投影;相关公式图已核对。 - 原始内容:The procedure G RADIENT -D ESCENT on the facing page takes as input a function f , an initial point x (0) ∈ ℝ n , a fixed step-size multiplier γ > 0, and a number T > 0 of steps to take. Each iteration of the for loop of lines 2–4 performs a step by computing the n -dimensional gradient at point x ( t ) and then moving distance γ in the opposite direction in the n -dimensional space. The complexity of computing the gradient depends on the function f and can sometimes be expensive. Line 3 sums the points visited. After the loop terminates, line 6 returns x-avg , the average of all the points visited except for the last one, x ( T ) . It might seem more natural to return x ( T ) , and in fact, in many circumstances, you might prefer to have the function return x ( T ) . For the version we will analyze, however, we use x-avg . G