A simple and efficient algorithm for fused lasso signal approximator with convex loss function

A simple and efficient algorithm for fused lasso signal approximator with convex loss function

We consider the augmented Lagrangian method (ALM) as a solver for the fused lasso signal approximator (FLSA) problem. The ALM is a dual method in which squares of the constraint functions are added as penalties to the Lagrangian. In order to apply this method to FLSA, two types of auxiliary variable...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Lichun, You, Yuan, Lian, Heng
Other Authors: School of Physical and Mathematical Sciences
Format: Article
Language:English
Published: 2013
Online Access:https://hdl.handle.net/10356/96858
http://hdl.handle.net/10220/13109
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-96858
record_format dspace
spelling sg-ntu-dr.10356-968582020-03-07T12:37:10Z A simple and efficient algorithm for fused lasso signal approximator with convex loss function Wang, Lichun You, Yuan Lian, Heng School of Physical and Mathematical Sciences We consider the augmented Lagrangian method (ALM) as a solver for the fused lasso signal approximator (FLSA) problem. The ALM is a dual method in which squares of the constraint functions are added as penalties to the Lagrangian. In order to apply this method to FLSA, two types of auxiliary variables are introduced to transform the original unconstrained minimization problem into a linearly constrained minimization problem. Each updating in this iterative algorithm consists of just a simple one-dimensional convex programming problem, with closed form solution in many cases. While the existing literature mostly focused on the quadratic loss function, our algorithm can be easily implemented for general convex loss. We also provide some convergence analysis of the algorithm. Finally, the method is illustrated with some simulation datasets. 2013-08-15T06:47:01Z 2019-12-06T19:35:47Z 2013-08-15T06:47:01Z 2019-12-06T19:35:47Z 2012 2012 Journal Article Wang, L., You, Y.,& Lian, H. (2013). A simple and efficient algorithm for fused lasso signal approximator with convex loss function. Computational Statistics, 28(4), 1699-1714. https://hdl.handle.net/10356/96858 http://hdl.handle.net/10220/13109 10.1007/s00180-012-0373-6 en Computational statistics
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
description We consider the augmented Lagrangian method (ALM) as a solver for the fused lasso signal approximator (FLSA) problem. The ALM is a dual method in which squares of the constraint functions are added as penalties to the Lagrangian. In order to apply this method to FLSA, two types of auxiliary variables are introduced to transform the original unconstrained minimization problem into a linearly constrained minimization problem. Each updating in this iterative algorithm consists of just a simple one-dimensional convex programming problem, with closed form solution in many cases. While the existing literature mostly focused on the quadratic loss function, our algorithm can be easily implemented for general convex loss. We also provide some convergence analysis of the algorithm. Finally, the method is illustrated with some simulation datasets.
author2 School of Physical and Mathematical Sciences
author_facet School of Physical and Mathematical Sciences
Wang, Lichun
You, Yuan
Lian, Heng
format Article
author Wang, Lichun
You, Yuan
Lian, Heng
spellingShingle Wang, Lichun
You, Yuan
Lian, Heng
A simple and efficient algorithm for fused lasso signal approximator with convex loss function
author_sort Wang, Lichun
title A simple and efficient algorithm for fused lasso signal approximator with convex loss function
title_short A simple and efficient algorithm for fused lasso signal approximator with convex loss function
title_full A simple and efficient algorithm for fused lasso signal approximator with convex loss function
title_fullStr A simple and efficient algorithm for fused lasso signal approximator with convex loss function
title_full_unstemmed A simple and efficient algorithm for fused lasso signal approximator with convex loss function
title_sort simple and efficient algorithm for fused lasso signal approximator with convex loss function
publishDate 2013
url https://hdl.handle.net/10356/96858
http://hdl.handle.net/10220/13109
_version_ 1681035611720384512

Similar Items