I was trying to solve a problem where the basis matrix contains the components of $\sin(nx)$, $\cos(nx)$, $\sinh(nx)$ and $\cosh(nx)$.

Say the $n$ varies from 1 to 100. While solving the lasso linear regression, I should get the sparse coefficients on say $n=10$ for each of the components. To be clear say the data obtained from the equation is $y= \alpha \sin(10x) + \beta \cos(10x) + \gamma \sinh(10x) + \delta \cosh(10x)$.

I am getting some arbitrary coefficients and that is not representing the equation.

What am I doing wrong?

  • $\begingroup$ Are you trying to solve $ \arg \min_{x} \frac{1}{2} {\left\| A x - b \right\|}_{2}^{2} + \lambda {\left\| x \right\|}_{1} $? $\endgroup$ – Royi Mar 1 '20 at 11:46

Your Answer

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

Browse other questions tagged or ask your own question.