Tor Lattimore

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.

Decision-making in the face of uncertainty is a significant challenge in machine learning, and the multi-armed bandit model is a commonly used framework to address it. This comprehensive and rigorous introduction to the multi-armed bandit problem examines all the major settings, including stochastic, adversarial, and Bayesian frameworks. A focus on both mathematical intuition and carefully worked proofs makes this an excellent reference for established researchers and a helpful resource for graduate students in computer science, engineering, statistics, applied mathematics and economics. Linear bandits receive special attention as one of the most useful models in applications, while other chapters are dedicated to combinatorial bandits, ranking, non-stationary problems, Thompson sampling and pure exploration. The book ends with a peek into the world beyond bandits with an introduction to partial monitoring and learning in Markov decision processes.