Foundations and Trends® in Optimization > Vol 2 > Issue 3-4

Introduction to Online Convex Optimization

Elad Hazan, Princeton University, USA, ehazan@cs.princeton.edu
 
Suggested Citation
Elad Hazan (2016), "Introduction to Online Convex Optimization", Foundations and TrendsĀ® in Optimization: Vol. 2: No. 3-4, pp 157-325. http://dx.doi.org/10.1561/2400000013

Published: 30 Aug 2016
© 2016 E. Hazan
 
Subjects
Optimization,  Online learning
 

Free Preview:

Article Help

Share

Download article
In this article:
1. Introduction
2. Basic concepts in convex optimization
3. First order algorithms for online convex optimization
4. Second order methods
5. Regularization
6. Bandit Convex Optimization
7. Projection-free Algorithms
8. Games, Duality and Regret
9. Learning Theory, Generalization and OCO
Acknowledgements
References

Abstract

This monograph portrays optimization as a process. In many practical applications the environment is so complex that it is infeasible to lay out a comprehensive theoretical model and use classical algorithmic theory and mathematical optimization. It is necessary as well as beneficial to take a robust approach, by applying an optimization method that learns as one goes along, learning from experience as more aspects of the problem are observed. This view of optimization as a process has become prominent in varied fields and has led to some spectacular success in modeling and systems that are now part of our daily lives.

DOI:10.1561/2400000013
ISBN: 978-1-68083-170-2
190 pp. $99.00
Buy book
 
ISBN: 978-1-68083-171-9
190 pp. $260.00
Buy E-book
Table of contents:
1. Introduction
2. Basic concepts in convex optimization
3. First order algorithms for online convex optimization
4. Second order methods
5. Regularization
6. Bandit Convex Optimization
7. Projection-free Algorithms
8. Games, Duality and Regret
9. Learning Theory, Generalization and OCO
Acknowledgements
References

Introduction to Online Convex Optimization

Introduction to Online Convex Optimization portrays optimization as a process. In many practical applications the environment is so complex that it is infeasible to lay out a comprehensive theoretical model and use classical algorithmic theory and mathematical optimization. It is necessary as well as beneficial to take a robust approach, by applying an optimization method that learns as one goes along, learning from experience as more aspects of the problem are observed. This view of optimization as a process has become prominent in varied fields and has led to some spectacular success in modeling and systems that are now part of our daily lives.

Introduction to Online Convex Optimization is intended to serve as a reference for a self-contained course on online convex optimization and the convex optimization approach to machine learning for the educated graduate student in computer science/electrical engineering/ operations research/statistics and related fields. It is also an ideal reference for the researcher diving into this fascinating world at the intersection of optimization and machine learning.

 
OPT-013