1st Edition
Sparse Modeling Theory, Algorithms, and Applications
Introduction. Sparse Recovery: Problem Formulations. Theoretical Results (Deterministic Part). Theoretical Results (Probabilistic Part). Algorithms for Sparse Recovery Problems. Beyond LASSO: Structured Sparsity. Beyond LASSO: Other Loss Functions. Sparse Graphical Models. Sparse Matrix Factorization: Dictionary Learning and Beyond. Epilogue. Appendix. Bibliography. Index.
Biography
Irina Rish, Genady Grabarnik
"… an excellent introductory book for branching off into aspects of sparse modeling; it is also good for advanced students since it is contains an appendix with some of the mathematical background needed to learn from this book, including topics such as eigentheory, discrete Fourier transform, and subgaussian random variables. I very much recommend this book for researchers and students alike."
—Computing Reviews, May 2015"A comprehensive, clear, and well-articulated book on sparse modeling. This book will stand as a prime reference to the research community for many years to come."
—Ricardo Vilalta, Department of Computer Science, University of Houston"This book provides a modern introduction to sparse methods for machine learning and signal processing, with a comprehensive treatment of both theory and algorithms. Sparse Modeling is an ideal book for a first-year graduate course."
—Francis Bach, INRIA - École Normale Supérieure, Paris
