Get the latest tech news
Are polynomial features the root of all evil? (2024)
There is a well-known myth in the machine learning community - high degree polynomials are bad for modeling. In this post we debunk this myth.
Vladimir Vapnik, in his famous book “The Nature of Statistical Learning Theory” which is cited more than 100,000 times as of today, coined the approximation vs. estimation balance. We will study them more in depth in the next posts, but at this stage I would like to point out two simple properties that give an intuitive explanation of why they’re useful in machine learning. Their main advantage is ease of use - we can use high degree polynomials to exploit their approximation power, and easily control model complexity with just one hyperparameter - the regularization coefficient.
Or read this on Hacker News