Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar: Foundations of machine learning, second edition

The MIT Press, Cambridge, MA, 2018, 504 pp., CDN $96.53 (hardback), ISBN 9780262039406
  • Li-Pang ChenEmail author
Book Review

In modern developments of statistics, machine learning has become more and more popular. Generally, machine learning methods aim to improve performance of model developments or to make accurate prediction such as classification. In the computational perspective, a plenty of machine learning references has been published and widely read (e.g., Hastie et al. 2008; James et al. 2017). However, in theoretical perspective, it seems that there is a little reference to discuss theoretical machine learning and provide rigorous justifications. Fortunately, the authors M. Mohri, A. Rostamizadeh, and A. Talwalkar published a book entitled “Foundations of Machine Learning”, and we now have second edition in 2018. Different from the first edition, the second edition includes more materials such as model selection and entropy models. The main advantages of this book include clear presentations of machine learning in theoretical perspectives, many important theorems with rigorous proofs, and many...



  1. Hastie T, Tibshirani R, Friedman J (2008) The elements of statistical learning: data mining, inference, and prediction. Springer, New YorkzbMATHGoogle Scholar
  2. James G, Witten D, Hastie T, Tibshirani R (2017) An introduction to statistical learning: with applications in R. Springer, New YorkzbMATHGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Statistics and Actuarial ScienceUniversity of WaterlooWaterlooCanada

Personalised recommendations