Convergence analysis of the approximate proximal splitting method for non-smooth convex optimization
2014-05
Loading...
View/Download File
Persistent link to this item
Statistics
View StatisticsJournal Title
Journal ISSN
Volume Title
Title
Convergence analysis of the approximate proximal splitting method for non-smooth convex optimization
Authors
Published Date
2014-05
Publisher
Type
Thesis or Dissertation
Abstract
Consider a class of convex minimization problems for which the objective function is the sum of a smooth convex function and a non-smooth convex regularity term. This class of problems includes several popular applications such as compressive sensing and sparse group LASSO. In this thesis, we introduce a general class of approximate proximal splitting (APS) methods for solving such minimization problems. Methods in the APS class include many well-known algorithms such as the proximal splitting method (PSM), the block coordinate descent method (BCD) and the approximate gradient projection methods for smooth convex optimization. We establish the linear convergence of APS methods under a local error bound assumption. Since the latter is known to hold for compressive sensing and sparse group LASSO problems, our analysis implies the linear convergence of the BCD method for these problems without strong convexity assumption.
Description
University of Minnesota M.S. thesis. May 2014. Major: Electrical Engineering. Advisor: Zhi-Quan Luo. 1 computer file (PDF); v, 46 pages, appendix A.
Related to
Replaces
License
Series/Report Number
Funding information
Isbn identifier
Doi identifier
Previously Published Citation
Suggested citation
Kadkhodaie Elyaderani, Mojtaba. (2014). Convergence analysis of the approximate proximal splitting method for non-smooth convex optimization. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/165536.
Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.