A Modern Introduction to Online Learning
Francesco Orabona

TL;DR
This book provides a comprehensive, accessible introduction to online learning, covering algorithms, theory, and applications within the framework of Online Convex Optimization and regret minimization.
Contribution
It offers a modern, unified presentation of online learning algorithms, including adaptive, parameter-free methods, and extends to advanced topics like bandits and non-stationary regret analysis.
Findings
Introduces first- and second-order algorithms for convex losses
Discusses adaptive and parameter-free online learning methods
Explores applications beyond traditional online learning domains
Abstract
In this book, I introduce the basic concepts of Online Learning through the modern view of Online Convex Optimization. Here, online learning refers to the framework of regret minimization under worst-case assumptions. I present first-order and second-order algorithms for online learning with convex losses, in Euclidean and non-Euclidean settings. All the algorithms are clearly presented as instantiation of Online Mirror Descent or Follow-The-Regularized-Leader and their variants. Particular attention is given to the issue of tuning the parameters of the algorithms and learning in unbounded domains, through adaptive and parameter-free online learning algorithms. Non-convex losses are addressed through convex surrogate losses and randomization. The bandit setting is also briefly discussed, touching on the problem of adversarial and stochastic multi-armed bandits. Finally, I also cover…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
