Regularization Methods for Machine Learning

The Regularization Methods for Machine Learning (RegML) is a week long course on Machine Learning, including theoretical as well as practical sessions.

Among the variety of approaches and ideas in modern computational learning, RegML focuses on a core class of methods, namely regularization methods, which represent a fundamental set of concepts and techniques allowing to treat in a unified way a huge class of diverse approaches, while providing the tools to design new ones. Starting from classical notions of smoothness, shrinkage and margin, RegML covers state of the art techniques based on the concepts of geometry (e.g. manifold learning), sparsity, low rank, allowing to design algorithm for tasks such as supervised learning, feature selection, structured prediction, multitask learning and model selection.



  • The RegML 2020 course page is now online here.