知识卡片

普通读书笔记卡 · 3711

凸函数的局部极小也是全局极小

理解等级:中级

凸性要求任意两点间的函数值不高于端点函数值的线性插值。若某个局部极小仍高于另一个点,沿两点连线取足够近的点就会得到更低值,产生矛盾。

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

      A convex function has the property that any local minimum is also a global minimum. To verify this property, consider inequality (33.18), and suppose for the purpose of contradiction that x is a local minimum but not a global minimum and y ≠ x is a global minimum, so f(y) < f(x). Then we have f(λx + (1 – λ)y) ≤ λf(x) + (1 – λ)f(y) (by inequality (33.18)) < λf(x) + (1 – λ)f(x) = f(x). Thus, letting approach 1, we see that there is another point near x, say x′, such that f(x′) < f(x), so x is not a local minimum. Convex functions have several useful properties. The first property, whose proof we leave as Exercise 33.3-1, says that a convex function always lies above its tangent hyperplane. In the context of gradient descent, angle brackets denote the notation

    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:A convex function has the property that any local minimum is also a global minimum. To verify this property, consider inequality (33.18), and suppose for the purpose of contradiction that x is a local minimum but not a global minimum and y ≠ x is a global minimum, so f ( y ) < f ( x ). Then we have f ( λ x + (1 – λ ) y ) ≤ λf ( x ) + (1 – λ ) f ( y ) (by inequality (33.18)) < λf ( x ) + (1 – λ ) f ( x ) = f ( x ). Thus, letting approach 1, we see that there is another point near x , say x ′, such that f ( x ′) < f ( x ), so x is not a local minimum. Convex functions have several useful properties. The first property, whose proof we leave as Exercise 33.3-1, says that a convex function always lies above its tangent hyperplane. In the context of gradient descent, angle brackets denote the notation