Understanding Machine Learning

Shalev-Shwartz, ShaiShai Shalev-Shwartz is an Associate Professor at the School of Computer Science and Engineering at the Hebrew University of Jerusalem, Israel.Ben-David, ShaiShai Ben-David is a Professor in the School of Computer Science at the University of Waterloo, Canada.

Machine learning is one of the fastest growing areas of computer science, with far-reaching applications. The aim of this textbook is to introduce machine learning, and the algorithmic paradigms it offers, in a principled way. The book provides a theoretical account of the fundamentals underlying machine learning and the mathematical derivations that transform these principles into practical algorithms. Following a presentation of the basics, the book covers a wide array of central topics unaddressed by previous textbooks. These include a discussion of the computational complexity of learning and the concepts of convexity and stability; important algorithmic paradigms including stochastic gradient descent, neural networks, and structured output learning; and emerging theoretical concepts such as the PAC-Bayes approach and compression-based bounds. Designed for advanced undergraduates or beginning graduates, the text makes the fundamentals and algorithms of machine learning accessible to students and non-expert readers in statistics, computer science, mathematics and engineering.

Introduces machine learning and its algorithmic paradigms, explaining the principles behind automated learning approaches and the considerations underlying their usage.

1. Introduction; Part I. Foundations: 2. A gentle start; 3. A formal learning model; 4. Learning via uniform convergence; 5. The bias-complexity trade-off; 6. The VC-dimension; 7. Non-uniform learnability; 8. The runtime of learning; Part II. From Theory to Algorithms: 9. Linear predictors; 10. Boosting; 11. Model selection and validation; 12. Convex learning problems; 13. Regularization and stability; 14. Stochastic gradient descent; 15. Support vector machines; 16. Kernel methods; 17. Multiclass, ranking, and complex prediction problems; 18. Decision trees; 19. Nearest neighbor; 20. Neural networks; Part III. Additional Learning Models: 21. Online learning; 22. Clustering; 23. Dimensionality reduction; 24. Generative models; 25. Feature selection and generation; Part IV. Advanced Theory: 26. Rademacher complexities; 27. Covering numbers; 28. Proof of the fundamental theorem of learning theory; 29. Multiclass learnability; 30. Compression bounds; 31. PAC-Bayes; Appendix A. Technical lemmas; Appendix B. Measure concentration; Appendix C. Linear algebra.