Shai Ben-David Shai Shalev-ShwartzCambridge University Press, 6/30/2014EAN 9781107057135, ISBN10: 1107057132Hardcover, 424 pages, 26 x 18.3 x 2.8 cmLanguage: EnglishMachine 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.1. IntroductionPart I. Foundations2. A gentle start3. A formal learning model4. Learning via uniform convergence5. The bias-complexity trade-off6. The VC-dimension7. Non-uniform learnability8. The runtime of learningPart II. From Theory to Algorithms9. Linear predictors10. Boosting11. Model selection and validation12. Convex learning problems13. Regularization and stability14. Stochastic gradient descent15. Support vector machines16. Kernel methods17. Multiclass, ranking, and complex prediction problems18. Decision trees19. Nearest neighbor20. Neural networksPart III. Additional Learning Models21. Online learning22. Clustering23. Dimensionality reduction24. Generative models25. Feature selection and generationPart IV. Advanced Theory26. Rademacher complexities27. Covering numbers28. Proof of the fundamental theorem of learning theory29. Multiclass learnability30. Compression bounds31. PAC-BayesAppendix A. Technical lemmasAppendix B. Measure concentrationAppendix C. Linear algebra.
