Elad Hazan is Professor of Computer Science at Princeton University and cofounder and director of Google AI Princeton. 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.
Preface xi
Acknowledgments xv
List of Figures xvii
List of Symbols xix
1 Introduction 1
2 Basic Concepts in Convex Optimization 15
3 First-Order Algorithms for Online Convex Optimization 37
4 Second-Order Methods 49
5 Regularization 63
6 Bandit Convex Optimization 89
7 Projection-Free Algorithms 107
8 Games, Duality and Regret 123
9 Learning Theory, Generalization, and Online Convex Optimization 133
10 Learning in Changing Environments 147
11 Boosting and Regret 163
12 Online Boosting 171
13 Blackwell Approachability and Online Convex Optimization 181
Notes 191
References 193
Index 207