Metric Learning

Aurélien Bellet received his Ph.D. in Machine Learning from the University of Saint-Etienne (France) in 2012. His work focused on algorithmic and theoretical aspects of metric and similarity learning. After completing his thesis, he was a postdoctoral researcher at the University of Southern California, where he worked on large-scale and distributed machine learning with applications to automatic speech recognition. He is currently a postdoctoral researcher at Telecom ParisTech (France), working on machine learning for big data.Amaury Habrard received a Ph.D. in Machine Learning in 2004 from the University of Saint-Etienne. He was Assistant Professor at the Laboratoire dInformatique Fondamentale of Aix-Marseille University until 2011, where he received a habilitation thesis in 2010. He is currently Professor in the Machine Learning group at the Hubert Curien laboratory of the University of Saint-Etienne. His research interests include metric learning, transfer learning, online learningand learning theory.Marc Sebban received a Ph.D. in Machine Learning in 1996 from the Universite of Lyon 1. After four years spent at the French West Indies and Guyana University as Assistant Professor, he got a position of Professor in 2002 at the University of Saint-Etienne (France). Since 2010, he is the head of the Machine Learning group and the director of the Computer Science, Cryptography and Imaging department of the Hubert Curien laboratory. His research interests focus on ensemble methods, metric learning, transfer learning and more generally on statistical learning theory.

• Introduction.- Metrics.- Properties of Metric Learning Algorithms.- Linear Metric Learning.- Nonlinear and Local Metric Learning.- Metric Learning for Special Settings.- Metric Learning for Structured Data.- Generalization Guarantees for Metric Learning.- Applications.- Conclusion.- Bibliography.- Authors' Biographies .