Machine Learning with Spark - Second Edition

Least squares regression

You might recall from Chapter 6, Building a Classification Model with Spark, that there are a variety of loss functions that can be applied to generalized linear models. The loss function used for least squares is the squared loss, which is defined as follows:

½ (w^Tx - y)²

Here, as for the classification setting, y is the target variable (this time, real valued), w is the weight vector, and x is the feature vector.

The related link function is the identity link, and the decision function is also the identity function, as generally, no thresholding is applied in regression. So, the model's prediction is simply y = w^Tx.

The standard least squares regression in ML library does not use regularization. Regularization is ...