Share & grow the world's knowledge!

- Snatch1967 on probiotic vs prebiotic, where does it come from? And how do we know which foods to ferment to produce friendly probiotics?
- Unhappy_Kumquat on How are scientists able to say that a random species is extinct? Did they have to look everywhere?
- druppolo on eli5 Why do old pc games that look good run better than new PC games that look bad
- dogeyo_to_tokyo on How are scientists able to say that a random species is extinct? Did they have to look everywhere?
- Birdie121 on How are scientists able to say that a random species is extinct? Did they have to look everywhere?

Copyright © 2022 AnswerCult

It usually works by shrinking the coefficients you get at the end. The coefficients get shrunk because there is a penalty applied. Normally you’re essentially minimizing the square error by finding the best coefficients. But in regularization, you add a penalty for each additional coefficient based on it’s size. So unless a coefficient explains a lot of variance to overcome the penalty, it will get shrunk toward 0.

This whole process is nice because a regular linear regression optimizes explained variance, but at the cost of additional bias (the coefficients are fit to the data you have, not the data you don’t). The penalty introduces some bias in the likelihood being optimized (shrinkage) to try to find the optimum balance of variance explained and minimal bias. Rather than just optimize variance explained.