This compact volume is part of the SpringerBriefs series, which publishes “concise summaries of cutting-edge research and practical applications across a wide spectrum of fields” [1]. This book discusses robust data mining, which involves applications of robust optimization in data mining. The authors present the most popular algorithms, along with the solutions for the problems that are treated in their four chapters: “Least Squares Problems,” “Principal Component Analysis,” “Linear Discriminant Analysis,” and “Support Vector Machines.” These chapters are supported by an introduction and conclusion.
Each chapter shows in detail how to solve some important practical problems, and each can be studied independently. Chapter 2 discusses Cholesky factorization, QR factorization, and singular value decomposition. Chapter 3 covers linear least squares and principal component analysis. Chapter 4 focuses on robust discriminant analysis, and chapter 5 discusses optimization problems solved with support vector machines (SVMs). The book also has two appendices on optimality conditions and dual norms, mathematical concepts that are useful in understanding the previous chapters.
Although the authors say that the book is for junior researchers, readers should have a very good understanding of linear programming and mathematical formulations, since all of the chapters are completely based on these concepts.