# Coordinate descent for Lasso, Question about algorithm

I'm not sure why the algorithm computes $$c_k$$ with $$\sum_{j \neq k} w_j x_{i, j}$$. Why does one need to ignore the $$k^{th}$$ feature here? I'm not sure how this is derived. Is this the result of taking the gradient with respect to the $$k^{th}$$ feature?

Also what exactly is $$a_k$$ and $$c_k$$?

• I suspect you will need to give us some context: e.g., to tell us what the notation represents, and where you're reading this. Please credit the original source of all copied material: cs.stackexchange.com/help/referencing – D.W. Mar 29 at 2:26
• You could also formally state the problem you are trying to optimize. I suspect that it's the least squares regression with Lasso regularization, but the update equations are not what I would expect. – Dmitry Mar 29 at 3:37
• This question is more appropriate for Cross Validated, where it might have already been answered: stats.stackexchange.com/questions/123672/…. – Yuval Filmus Apr 2 at 6:53