{"product_id":"introduction-to-online-convex-optimization-second-edition-isbn-9780262046985","title":"Introduction to Online Convex Optimization, second edition","description":"\u003cb\u003eNew edition of a graduate-level textbook on that focuses on online convex optimization, a machine learning framework that views optimization as a process.\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003eIn 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. \u003ci\u003eIntroduction to Online Convex Optimization\u003c\/i\u003e 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. \u003cbr\u003e\u003cbr\u003eBased on the “Theoretical Machine Learning” course taught by the author at Princeton University, the second edition of this widely used graduate level text features:\u003cbr\u003e\u003cli\u003eThoroughly updated material throughout\u003c\/li\u003e\u003cli\u003eNew chapters on boosting, adaptive regret, and approachability and expanded exposition on optimization\u003c\/li\u003e\u003cli\u003eExamples of applications, including prediction from expert advice, portfolio selection, matrix completion and recommendation systems, SVM training, offered throughout \u003c\/li\u003e\u003cli\u003eExercises that guide students in completing parts of proofs\u003c\/li\u003ePreface xi\u003cbr\u003eAcknowledgments xv\u003cbr\u003eList of Figures xvii\u003cbr\u003eList of Symbols xix\u003cbr\u003e1 Introduction 1\u003cbr\u003e2 Basic Concepts in Convex Optimization 15\u003cbr\u003e3 First-Order Algorithms for Online Convex Optimization 37\u003cbr\u003e4 Second-Order Methods 49\u003cbr\u003e5 Regularization 63\u003cbr\u003e6 Bandit Convex Optimization 89\u003cbr\u003e7 Projection-Free Algorithms 107\u003cbr\u003e8 Games, Duality and Regret 123\u003cbr\u003e9 Learning Theory, Generalization, and Online Convex Optimization 133\u003cbr\u003e10 Learning in Changing Environments 147\u003cbr\u003e11 Boosting and Regret 163\u003cbr\u003e12 Online Boosting 171\u003cbr\u003e13 Blackwell Approachability and Online Convex Optimization 181\u003cbr\u003eNotes 191\u003cbr\u003eReferences 193\u003cbr\u003eIndex 207Elad Hazan is Professor of Computer Science at Princeton University and cofounder and director of Google AI Princeton\u003cb\u003e.\u003c\/b\u003e An innovator in the design and analysis of algorithms for basic problems in machine learning and optimization, he is coinventor of the AdaGrad optimization algorithm for deep learning, the first adaptive gradient method.","brand":"The MIT Press","offers":[{"title":"Default Title","offer_id":46302886625509,"sku":"NP9780262046985","price":60.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9780262046985.jpg?v=1767730146","url":"https:\/\/k12savings.com\/products\/introduction-to-online-convex-optimization-second-edition-isbn-9780262046985","provider":"K12savings","version":"1.0","type":"link"}