|
High-Dimensional Data Analysis with
Low-Dimensional Models:
|
|
|
High-Dimensional Data Analysis with
Low-Dimensional Models:
|
The book covers new mathematical (statistical, geometrical, computational) principles for high-dimensional data analysis, with scalable optimization methods and their applications in important real-world problems such as scientific imaging, wideband communications, face recognition, 3D vision, and deep networks. Comprehensive in its approach, the book provides unified coverage of many different low-dimensional models and analytical techniques, including sparse, low-rank, and deep network models, with both convex and nonconvex formulations.
This textbbook is intended for an introductatory graduate course that helps students establish a solid foundation for the areas of data science, signal processing, optimization, and machine learning. Early versions of this book have been used as the textbook for courses at University of Illinois, University of Californina at Berkeley, Columbia University, Tsinghua University, ShanghaiTech University, and University of Michigan etc.
@book{Wright-Ma-2022,
author = {John Wright and Yi Ma},
title = {High-Dimensional Data Analysis with Low-Dimensional Models:
Principles, Computation, and Applications},
publisher = {Cambridge University Press},
year = {2022}
}