One of the most classical results in high-dimensional learning theory provides a closed-form
expression for the generalisation error of binary classification with a single-layer teacher …

This statistical physics thesis focuses on the study of three kinds of systems which display
repulsive interactions: eigenvalues of random matrices, non-crossing random walks and …

This thesis presents three main contributions to the understanding of machine learning
models by making use of statistical physics tools. First, we investigate the possible relation …