I read different articles including this answer.

Why is bias term not included in regularization, in general? I see some of the algorithms such as LinearSVC includes bias term in regularization. Also, is bias term used for only predicting minimum value possible when all weights are zero? What is its significance exactly?

  • $\begingroup$ In statistics bias term is usually called intercept. $\endgroup$ – kjetil b halvorsen Jul 6 '20 at 1:33