Hacker News new | ask | show | jobs
by R_haterade 3190 days ago
Excellent John D. Cook piece on the same subject: https://www.johndcook.com/blog/2010/01/19/dont-invert-that-m...
1 comments

That's a slightly different issue: the issue with solving normal equations directly is that the condition number of X^\top X is the square of the condition number of X, so it's much more significant than lu-vs-inv. It can matter a great deal for ill-conditioned linear regression problems where some features resemble each other.