Oracle Inequalities in Empirical Risk Minimization and Sparse Recovery Problems: École d’Été de Probabilités de Saint-Flour XXXVIII-2008

Provides a unified framework for machine learning problems (such as large margin classification), sparse recovery and low rank matrix problems Develops a variety of probabilistic inequalities for empirical processes needed to obtain error bounds in machine learning and sparse recovery Develops a comprehensive theory of excess risk bounds and oracle inequalities for penalized empirical risk minimization Includes supplementary material: sn.pub/extras