Learning curves for the multi-class teacher-student perceptron

Understand

One of the most classical results in high-dimensional learning theory provides a closed-form expression for the generalisation error of binary classification with the single-layer teacher-student perceptron on i.i.d.

• Gaussian inputs.
• Both Bayes-optimal estimation and empirical risk minimisation (ERM) were extensively analysed for this setting.
• At the same time, a considerable part of modern machine learning practice concerns multi-class classification.