知识卡片
海森矩阵正半定刻画二阶凸性
海森矩阵由目标函数对各坐标的二阶偏导组成。对二阶可微函数,海森矩阵处处正半定是凸性的判据;在线性系统的二次目标中,它就是对称矩阵A。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
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
The equivalent definition for a multidimensional function is that it is convex when its Hessian matrix is positive-semidefinite (see page 1222 for a definition), where the Hessian matrix (∇2f)(x) of a function f(x) is the matrix in which entry (i, j) is the partial derivative of f with respect to i and j: Analogous to the 1-dimensional case, the Hessian of f is just A, and so if A is a positive-semidefinite matrix, then we can use gradient descent to find a point x where Ax ≈ b. If R and L are not too large, then this method is faster than using
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[60000,65000))。
- 结论依据:原文第33.3节或章末题目、注记;相关公式图已核对,未解答书中练习。
- 原始内容:The equivalent definition for a multidimensional function is that it is convex when its Hessian matrix is positive-semidefinite (see page 1222 for a definition), where the Hessian matrix (∇ 2 f )( x ) of a function f ( x ) is the matrix in which entry ( i , j ) is the partial derivative of f with respect to i and j : Analogous to the 1-dimensional case, the Hessian of f is just A , and so if A is a positive-semidefinite matrix, then we can use gradient descent to find a point x where A x ≈ b . If R and L are not too large, then this method is faster than using