Nvidia Interview Question | Ridge Regression

Question

When might you want to use ridge regression instead of traditional linear regression? State some situations.

in progress 1
Dhruv2301 4 years 1 Answer 955 views Great Grand Master 0

Answer ( 1 )

  1. Ridge regression allow us to regularize coefficients. This means that the estimated coefficients are pushed towards 0, to make them work better on new data-sets

    Ridge regression is often used when the independent variables are colinear. One issue with colinearity is that the variance of the parameter estimate is huge. Ridge regression reduces this variance at the price of introducing bias to the estimates

    Ridge Regression, avoids over fitting by adding a penalty to models that have too large coefficients.

Leave an answer

Browse
Browse