In the derivation of the bias variance decomposition I miss a linear term in epsilon in equation 4.18.
I can see that this term (linear in epsilon) vanishes when we take the expectationvalue over x_star in eq 4.19, but not before.
Suggested change
If you have an idea on how to fix it, please let us know
Location Please provide:
Describe the mistake
In the derivation of the bias variance decomposition I miss a linear term in epsilon in equation 4.18. I can see that this term (linear in epsilon) vanishes when we take the expectationvalue over x_star in eq 4.19, but not before.
Suggested change If you have an idea on how to fix it, please let us know
Additional comments