Publisher's Synopsis
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 optimisation. Introduction to Online Convex Optimization presents a robust machine learning approach that contains elements of mathematical optimisation, game theory, and learning theory: an optimisation method that learns from experience as more aspects of the problem are observed. This view of optimisation as a process has led to some spectacular successes in modelling and systems that have become part of our daily lives. 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: · Thoroughly updated material throughout · New chapters on boosting, adaptive regret, and approachability and expanded exposition on optimisation · Examples of applications, including prediction from expert advice, portfolio selection, matrix completion and recommendation systems, SVM training, offered throughout · Exercises that guide students in completing parts of proofs Series Overview: Adaptive Computation and Machine Learning series promotes the unification of the many diverse strands of machine learning research and fosters high quality research and innovative applications. This series publishes works of the highest quality that advance the understanding and practical application of machine learning and adaptive computation.