Understanding Machine Learning

Discover the rapidly growing field of machine learning with this in-depth textbook. Covering the mathematical foundations and practical algorithms of machine learning, this book includes topics not found in other textbooks, such as computational complexity, convexity, and stability. Learn about important algorithmic paradigms such as neural networks and stochastic gradient descent, as well as emerging concepts like PAC-Bayes and compression-based bounds. This text is accessible to advanced undergraduate and beginning graduate students, as well as readers in statistics, computer science, mathematics, and engineering.