Update 2021JUN20.md

2021JUN20.md

@@ -46,14 +46,14 @@ d = 1500 # number of features
 # generate feature matrices - high quality
 Xtrain, Xtest = (randn(n, d) for _ ∈ 1:2)
 # low quality -- some columns are noisier
-noise_col = rand(1:d, Int(d * 0.2)) # 20% of the columns are noiser
+noise_col = rand(1:d, Int(d * 0.2)) # 20% of the columns of XL are noiser
 XLtrain = copy(Xtrain)
 XLtrain[:, noise_col] .+= randn(n, Int(d * 0.2))
 XLtest = copy(Xtest)
 XLtest[:, noise_col] .+= randn(n, Int(d * 0.2))
 [x .= exp.(x) for x ∈ [Xtrain, Xtest, XLtrain, XLtest]]
 
-# generate high quality coefficients - 60% of the coefficients are zeros.
+# generate high quality coefficients - 60% of the coefficients w are zeros.
 w=randn(d); w[rand(1:d, Int(d*0.6))] .= 0. 
 
 ytrain= logistic.(Xtrain*w); ytest = logistic.(Xtest * w)
@@ -61,7 +61,7 @@ ttrain = [x > 0.5 ? 1 : 0 for x in ytrain]
 ttest = [x > 0.5 ? 1: 0 for x in ytest]
 
 # low quality -- some columns are zero
-zero_col = rand(1:d, Int(d * 0.05)) # 5% of the columns are zero
+zero_col = rand(1:d, Int(d * 0.05)) # 5% of the columns in XL are zero
 [x .= exp.(x) for x ∈ [Xtrain, Xtest]]
 XLtrain = copy(Xtrain)
 XLtrain[:, zero_col] .= 0.