In a regularized regression model (ridge regression), the target function to be minimized is f
computer science
Description
In a regularized regression model (ridge regression), the
target function to be minimized is f ( β ) = ∑ i = 1 n ( y i − β x i ) 2 + λ β 2 where x i and y i are the observed
predictor and response values, n is the number of observations, λ is a given hyper-parameter, and β is the target parameter to be estimated. Use the gradient
descent method to find β respectively when λ = 1 , 10 , 100 . The observed data are as follows, i.e., n = 6 , x 1 = 10 , y 1 = 32 , x 6 = 22 , y 6 = 72 , etc.
|
i |
x |
y |
|
1 |
10 |
32 |
|
2 |
13 |
40 |
|
3 |
17 |
46 |
|
4 |
18 |
62 |
|
5 |
20 |
54 |
|
6 |
22 |
72 |
