Bandit Convex Optimisation

Erscheinungsjahr 2026
ISBN: 978-1-009-60759-9
Verlag: Cambridge University Press

Buch, Englisch, 277 Seiten

This comprehensive reference brings readers to the frontier of research on bandit convex optimization or zeroth-order convex optimization. The focus is on theoretical aspects, with short, self-contained chapters covering all the necessary tools from convex optimization and online learning, including gradient-based algorithms, interior point methods, cutting plane methods and information-theoretic machinery. The book features a large number of exercises, open problems and pointers to future research directions, making it ideal for students as well as researchers.

Autoren/Hrsg.

Lattimore, Tor

Inhaltsverzeichnis

Preface; 1. Introduction and problem statement; 2. Overview of methods and history; 3. Mathematical tools; 4. Bisection in one dimension; 5. Online gradient descent; 6. Self-concordant regularisation; 7. Linear and quadratic bandits; 8. Exponential weights; 9. Cutting plane methods; 10. Online Newton step; 11. Online Newton step for adversarial losses; 12. Gaussian optimistic smoothing; 13. Submodular minimisation; 14. Outlook; Appendix A. Miscellaneous; Appendix B. Concentration; Appendix C. Notation; Bibliography; Index.

Über Autor(innen)

Lattimore, Tor
Tor Lattimore is a researcher at Google DeepMind working on reinforcement learning, bandits, optimisation and the theory of machine learning. He is the co-author of an introductory book on bandit algorithms and has published nearly 100 conference and journal articles. He is an action editor for the Journal of Machine Learning Research.