High-Dimensional Data Analysis with Low-Dimensional Models
Principles, Computation, and Applications
John Wright author Yi Ma author
Format:Hardback
Publisher:Cambridge University Press
Published:13th Jan '22
Currently unavailable, and unfortunately no date known when it will be back
Connects fundamental mathematical theory with real-world problems, through efficient and scalable optimization algorithms.
A systematic introduction to the theory, algorithms, and applications of key mathematical models for data science. Covering applications including imaging, communication, and face recognition, with online code, it is ideal for senior/graduate students in computer science, data science, and electrical engineering. With foreword by Emmanuel Candès.Connecting theory with practice, this systematic and rigorous introduction covers the fundamental principles, algorithms and applications of key mathematical models for high-dimensional data analysis. Comprehensive in its approach, it provides unified coverage of many different low-dimensional models and analytical techniques, including sparse and low-rank models, and both convex and non-convex formulations. Readers will learn how to develop efficient and scalable algorithms for solving real-world problems, supported by numerous examples and exercises throughout, and how to use the computational tools learnt in several application contexts. Applications presented include scientific imaging, communication, face recognition, 3D vision, and deep networks for classification. With code available online, this is an ideal textbook for senior and graduate students in computer science, data science, and electrical engineering, as well as for those taking courses on sparsity, low-dimensional structures, and high-dimensional data. Foreword by Emmanuel Candès.
'Students will learn a lot from reading this book … They will learn about mathematical reasoning, they will learn about data models and about connecting those to reality, and they will learn about algorithms. The book also contains computer scripts so that we can see ideas in action, and carefully crafted exercises making it perfect for upper-level undergraduate or graduate-level instruction. The breadth and depth make this a reference for anyone interested in the mathematical foundations of data science.' Emmanuel Candès, Stanford University (from the foreword)
'At the very core of our ability to process data stands the fact that sources of information are structured. Modeling data, explicitly or implicitly, is our way of exposing this structure and exploiting it, being the essence of the fields of signal and image processing and machine learning. The past two decades have brought a revolution to our understanding of these facts, and this 'must-read' book provides the foundations of these recent developments, covering theoretical, numerical, and applicative aspects of this field in a thorough and clear manner.' Michael Elad, Technion – Israel Institute of Technology
ISBN: 9781108489737
Dimensions: 251mm x 175mm x 36mm
Weight: 1430g
650 pages