Foundations of Machine Learning

This graduate-level textbook introduces fundamental concepts and methods in machinelearning. It describes several important modern algorithms, provides the theoretical underpinningsof these algorithms, and illustrates key aspects for their application. The authors aim to presentnovel theoretical tools and concepts while giving concise proofs even for relatively advancedtopics. Foundations of Machine Learning fills the need for a general textbookthat also offers theoretical details and an emphasis on proofs. Certain topics that are oftentreated with insufficient attention are discussed in more detail here; for example, entire chaptersare devoted to regression, multi-class classification, and ranking. The first three chapters lay thetheoretical foundation for what follows, but each remaining chapter is mostly self-contained. Theappendix offers a concise probability review, a short introduction to convex optimization, tools forconcentration bounds, and several basic properties of matrices and norms used in thebook.

The book is intended for graduate students and researchers in machinelearning, statistics, and related areas; it can be used either as a textbook or as a reference textfor a research seminar.