The hyperplane of hard margin SVM with $\phi$ kernel is calculated as following that input space using $\phi$ to map to higher dimension space.


$$ \phi(x)=\left[ \begin{array}{c} \phi_1(x)=x_1^2\\ \phi_2(x)=x_2^2\\\phi_3(x)=x_1x_2\\\phi_4(x)=-x_1 \end{array} \right] $$

Which of the following can be a support vector?

$$ x=\left[ \begin{array}{c} +1\\ 1 \end{array} \right] $$ $$ y=\left[ \begin{array}{c} 1\\ -1 \end{array} \right] $$


  1. $\ x=$ YES, $\ y=$ No

  2. $\ x=$ YES, $\ y=$ YES

The correct answer is option $1$. My challenge is where is the trick in this question, because calculation by hand shown that none of them are support vectors? How can we choose an option here?

  • 2
    $\begingroup$ Can you also share how your thinking process is? i.e. why do you think that the given vectors are not SVs? $\endgroup$
    – gunes
    Jan 13 at 17:14
  • 2
    $\begingroup$ Please add the self-study tag & read its wiki. Then tell us what you understand thus far, what you've tried & where you're stuck. We'll provide hints to help you get unstuck. Please make these changes as just posting your homework & hoping someone will do it for you is grounds for closing. $\endgroup$ Jan 14 at 12:52

If 𝑓(𝜙(𝑥))=4𝜙1(𝑥)+9𝜙2(𝑥)+4𝜙3(𝑥) is the equation of the SVM, what in

the wikipedia entry for SVM is the formula $w^T x - b$, (or better $w^T \phi(x) - b$ after you use the kernel trick) then points in the support vector should have $f(\phi(x)) = \pm 1$ (see this figure in the wiki page).

So just plug in the values of the two points and check whether $f(\phi(x))$ and $f(\phi(y))$ is either +1 or -1.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.