Principles and Theory for Data Mining and Machine Learning (Springer Series in Statistics)

From the reviews:

“PhD level students, and researchers and practitioners in statistical learning and machine learning. ... text assumes a thorough training in undergraduate statistics and mathematics. Computed examples that include R code are scattered through the text. There are numerous exercises, many with commentary that sets out guidelines for exploration. ... The over-riding reason for staying with the independent, symmetric unimodal error model is surely that no one book can cover everything! Within these bounds, this book gives a careful treatment that is encyclopedic in its scope.” (John H. Maindonald, International Statistical Review, Vol. 79 (1), 2011)

“It is an appropriate textbook for a PhD level course and can also be used as a reference or for independent reading. ... an excellent resource for researchers and students interested in DMML. ... the authors have done an outstanding job of covering important topics and providing relevant statistical theory and computational resources. I can see myself teaching a statistical learning class using this book and comfortably recommend it to any researcher with a solid mathematical background who wants to be engaged in this field.” (Jeongyoun Ahn, Journal of the American Statistical Association, Vol. 106 (493), March, 2011)

“This book provides an encyclopedic monograph on this field from a statistical point of view. ... A salient feature of this book is its coverage of theoretical aspects of DMML techniques. ... Additionally, plenty of exercises and computational examples with R codes are provided to help one brush up on the technical content of the text.” (Kazuho Watanabe, Mathematical Reviews, Issue 2012 i)