0% found this document useful (0 votes)
18 views

Hw2 Kernel Trick 2021

The document discusses two exercises related to kernel methods in machine learning. The first exercise asks to show that a given function K is a positive definite kernel and describe its reproducing kernel Hilbert space. The second exercise asks to prove that a function belongs to a reproducing kernel Hilbert space if and only if subtracting it from the positive definite kernel results in another positive definite kernel.

Uploaded by

aymasrayman
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
18 views

Hw2 Kernel Trick 2021

The document discusses two exercises related to kernel methods in machine learning. The first exercise asks to show that a given function K is a positive definite kernel and describe its reproducing kernel Hilbert space. The second exercise asks to prove that a function belongs to a reproducing kernel Hilbert space if and only if subtracting it from the positive definite kernel results in another positive definite kernel.

Uploaded by

aymasrayman
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

”Kernel methods in machine learning”

Homework 2
Due February 3, 2021, 3pm
Julien Mairal and Jean-Philippe Vert

Exercice 1.
Let X be a set and F be a Hilbert space. Let Ψ : X → F, and K : X ×X → R
be:
∀x, x0 ∈ X , K(x, x0 ) = hΨ(x), Ψ(x0 )iF .
Show that K is a positive definite kernel on X , and describe its RKHS H.
(Hint: Show that any function of the form fw (x) = hΨ(x), wiF is in H, for
w ∈ F, and explicit its norm.)

Exercice 2.
Prove that for any p.d. kernel K on a space X , a function f : X → R belongs
to the RKHS H with kernel K if and only if there exists λ > 0 such that
K(x, x0 ) − λf (x)f (x0 ) is p.d.
(Hint: you can use the result of Exercice 5.1. that we discussed in the course.)

You might also like