Algorithms for Sparsity-Constrained Optimization

  • Sohail Bahmani

Part of the Springer Theses book series (Springer Theses, volume 261)

Table of contents

  1. Front Matter
    Pages i-xxi
  2. Sohail Bahmani
    Pages 1-3
  3. Sohail Bahmani
    Pages 5-10
  4. Sohail Bahmani
    Pages 11-35
  5. Sohail Bahmani
    Pages 37-49
  6. Sohail Bahmani
    Pages 51-60
  7. Sohail Bahmani
    Pages 71-72
  8. Back Matter
    Pages 73-107

About this book


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.


Compressed Sensing Compressed Sensing GraSP Algorithm Linear Models Linear Regression Logistic Regression Model-Based Sparsity Nonlinear Inference Smooth Cost Functions

Authors and affiliations

  • Sohail Bahmani
    • 1
  1. 1.Carnegie Mellon UniversityPittsburghUSA

Bibliographic information

  • DOI
  • Copyright Information Springer International Publishing Switzerland 2014
  • Publisher Name Springer, Cham
  • eBook Packages Engineering
  • Print ISBN 978-3-319-01880-5
  • Online ISBN 978-3-319-01881-2
  • Series Print ISSN 2190-5053
  • Series Online ISSN 2190-5061
  • About this book