原书出处
Introduction to Algorithms, Fourth Edition
33 第33章 机器学习算法
and then compute the number of iterations needed. That is, we can solve for T, obtaining
T = R2L2/ϵ2. The number of iterations thus depends on the square of R and L and, most importantly, on 1/ϵ2. (The definition of L from inequality (33.21) depends on T, but we may know an upper bound on L that doesn’t depend on the particular value of T.) Thus, if you want to halve your error bound, you need to run four times as many iterations. It is quite possible that we don’t really know R and L, since you’d need to know x* in order to know R (since R = ∥x(0) – x*∥), and you might not have an explicit upper bound on the gradient, which would provide L. You can, however, interpret
the analysis of gradient descent as a proof that there is some step size for which the pr
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Introduction to Algorithms, Fourth Edition/_epub-src/OEBPS/chapter033.xhtml
EPUB SHA-256:ec7ced04bb875b93983816aef7a667855a4b71c5cf53b63406b9439c74e27aea