Foundations of Machine Learning, second edition (Adaptive Computation and Machine Learning series)

This comprehensive machine learning textbook provides a solid foundation in analysis and theory for graduate students and researchers.

With a focus on Probably Approximately Correct (PAC) learning framework, generalization bounds based on Rademacher complexity and VC-dimension, Support Vector Machines (SVMs), kernel methods, boosting, online learning, multi-class classification, ranking, regression, algorithmic stability, dimensionality reduction, learning automata and languages, and reinforcement learning, this book covers a wide range of topics in machine learning.

The second edition includes three new chapters on model selection, maximum entropy models, and conditional entropy models, as well as expanded coverage of concentration inequalities and a new entry on information theory.

More than half of the exercises are new to this edition.

Whether you're a graduate student or a researcher looking for a comprehensive introduction to machine learning, or just someone interested in learning more about this exciting field, Foundations of Machine Learning is the perfect choice.