Activity: Participating in or organising an event › Participant of a conference, workshop, panel, session or tutorial
The main goal of this short course is to provide PhD students with an understanding of the most important aspects of the theory underlying sparse representation and, more in general, of sparsity as a form of regularization in learning problems. Students will have the opportunity to understand the main algorithms for i) computing sparse representations, ii) solve optimization problems involving sparsity as a regularization prior, ii) learning dictionaries yielding sparse for a given training set of signals. These methods have wide applicability in computer science, and these will be a useful background for their research.
In particular, this course aims at: • Presenting the most important aspects of the theory underlying sparse representations, and in particular the sparse-coding and dictionary-learning problems. • Illustrating the main algorithms for sparse coding and dictionary learning, with a particular emphasis on solutions of convex optimization problems that are widely encountered in engineering. • Providing an overview of sparsity as a general regularization prior in many inverse problems and the connection with LASSO in linear regression.