知识卡片
平滑凸函数有二次上界
β-平滑条件给出函数在x附近的二次上界:f(y)≤f(x)+⟨∇f(x),y−x⟩+(β/2)∥y−x∥²。
它限制局部增长速度,可用于分析更快的梯度下降界;不能和凸性的切线下界混同。
这张卡片看不懂?
这张卡片的反馈已满 10 条,暂时无法继续提交。
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
Another case in which gradient descent can be shown to perform better than the analysis in Section 33.3 suggests is for smooth convex functions. We say that a function is β-smooth if . This inequality goes in the opposite direction from the one for ≈-strong convexity. Better bounds on gradient descent are possible here as well. 1 Although the curve in Figure 33.4 looks concave, according to the definition of convexity that we’ll see below, the function f in the figure is convex. 2 A function f : ℝn → ℝ is closed
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[75000,78591))。
- 结论依据:第33章末注记以 Art_P1429 定义 β-平滑:f(y)≤f(x)+⟨∇f(x),y−x⟩+(β/2)∥y−x∥²;该式是局部二次上界,方向与凸性的切线下界相反。原书仅提示可得更好收敛界,此卡不冒充证明具体速率。
- 原始内容:Another case in which gradient descent can be shown to perform better than the analysis in Section 33.3 suggests is for smooth convex functions. We say that a function is β-smooth if . This inequality goes in the opposite direction from the one for ≈ -strong convexity. Better bounds on gradient descent are possible here as well. 1 Although the curve in Figure 33.4 looks concave, according to the definition of convexity that we’ll see below, the function f in the figure is convex. 2 A function f : ℝ n → ℝ is closed