Read more
b>New edition of a graduate-level textbook on that focuses on online convex optimization, a machine learning framework that views optimization as a process./b>br>br>In many practical applications, the environment is so complex that it is not feasible to lay out a comprehensive theoretical model and use classical algorithmic theory and/or mathematical optimization. Introduction to Online Convex Optimization presents a robust machine learning approach that contains elements of mathematical optimization, game theory, and learning theory: an optimization method that learns from experience as more aspects of the problem are observed. This view of optimization as a process has led to some spectacular successes in modeling and systems that have become part of our daily lives. br>br>Based on the “Theoretical Machine Learning” course taught by the author at Princeton University, the second edition of this widely used graduate level text features:br> b>•/b> Thoroughly updated material throughoutbr> b>•/b> New chapters on boosting, adaptive regret, and approachability and expanded exposition on optimizationbr> b>•/b> Examples of applications, including prediction from expert advice, portfolio selection, matrix completion and recommendation systems, SVM training, offered throughout br> b>•/b> Exercises that guide students in completing parts of proofs
