Algorithms for Sparsity-Constrained Optimization

This thesis demonstrates techniques that provide faster and more accurate solutions to a variety of problems in machine learning and signal processing. The author proposes a "greedy" algorithm, deriving sparse solutions with guarantees of optimality. The use of this algorithm removes many of the inaccuracies that occurred with the use of previous models.

List of contents

Introduction.- Preliminaries.- Sparsity-Constrained Optimization.- Background.- 1-bit Compressed Sensing.- Estimation Under Model-Based Sparsity.- Projected Gradient Descent for `p-constrained Least Squares.- Conclusion and Future Work.

About the author

Dr. Bahmani completed his thesis at Carnegie Mellon University and is currently employed by the Georgia Institute of Technology.

Summary

This thesis demonstrates techniques that provide faster and more accurate solutions to a variety of problems in machine learning and signal processing. The author proposes a "greedy" algorithm, deriving sparse solutions with guarantees of optimality. The use of this algorithm removes many of the inaccuracies that occurred with the use of previous models.

Product details

• Authors: Sohail Bahmani
• Publisher: Springer, Berlin
• Languages: English
• Product format: Hardback
• Released: 25.07.2013
• EAN: 9783319018805
• ISBN: 978-3-31-901880-5
• No. of pages: 107
• Dimensions: 162 mm x 239 mm x 15 mm
• Weight: 340 g
• Illustrations: XXI, 107 p. 13 illus., 12 illus. in color.
• Series: Springer Theses; Springer Theses
• Subject: Natural sciences, medicine, IT, technology > Technology > Electronics, electrical engineering, communications engineering