If training data is linearly separable, then the Perceptron algorithm is guaranteed to find a linear separator.

Perceptron Convergence Theorem

If there is:

  • Some such that for all
    • (Margin of with respect to dataset is )
    • (Magnitude of data points is bounded by R)

Then:

  • Perceptron will make at most mistakes

Proof: Perception_Convergence_Proof