Binary Classification

Binary Classifiication is the most classic problem in ML.

Binary Classification solves the problem,

$$x_i \in \mathbb{R}^n, y_i \in \mathbb{B}, i = 1, 2, \ldots, n$$

Where $\mathbb{B} = \{0,1\}$ or sometimes, $\mathbb{B} = \{-1,1\}$.

And a train dataset,

$$\mathcal{D} = \{(x_1, y_1), (x_2, y_2), \ldots, (x_n, y_n)\}$$

Finds the best fit $f$ for,

$$\hat{y} = f(x)$$

By best fit, we typically mean to minimize a loss value. Depending on the algorithm, the loss function can be different. However, for binary classification, there are also some method based on rules, what we call the covering algorithm.