國立高雄大學圖資館 |

Language: English

Back

Stable and Efficient Sparse Recovery...

Harvard University.

Stable and Efficient Sparse Recovery for Machine Learning and Wireless Communication.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Stable and Efficient Sparse Recovery for Machine Learning and Wireless Communication.
Author:	Lin, Tsung-Han.
Description:	132 p.
Notes:	Source: Dissertation Abstracts International, Volume: 75-10(E), Section: B.
Notes:	Adviser: H. T. Kung.
Contained By:	Dissertation Abstracts International75-10B(E).
Subject:	Computer science.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3626838
ISBN:	9781321018943

Stable and Efficient Sparse Recovery for Machine Learning and Wireless Communication.
Lin, Tsung-Han.

Stable and Efficient Sparse Recovery for Machine Learning and Wireless Communication. - 132 p.

Source: Dissertation Abstracts International, Volume: 75-10(E), Section: B.

Thesis (Ph.D.)--Harvard University, 2014.

This item must not be sold to any third party vendors.

Recent theoretical study shows that the sparsest solution to an underdetermined linear system is unique, provided the solution vector is sufficiently sparse, and the operator matrix has sufficiently incoherent column vectors. In addition, efficient algorithms have been discovered to find such solutions. This intriguing result opens a new door for many potential applications. In this thesis, we study the design of a class of greedy algorithms that are extremely efficient, e.g., Orthogonal Matching Pursuit (OMP). These greedy algorithms suffer from a stability issue that the greedy selection approach always make locally optimal decisions, thereby easily biasing and mistaking the solutions in particular under data noise. We propose a solution approach that in designing greedy algorithms, new constraints can be devised by leveraging application-specific insights and incorporated into the algorithms. Given that sparse recovery problems by definition are underdetermined, introducing additional constraints can significantly improve the stability of greedy algorithms, yet retain their efficiency.

ISBN: 9781321018943Subjects--Topical Terms:

199325
Computer science.

Stable and Efficient Sparse Recovery for Machine Learning and Wireless Communication.
LDR:03349nmm a2200289 4500 001 457670
005 20150805065218.5
008 150916s2014 ||||||||||||||||| ||eng d
020 $a 9781321018943
035 $a (MiAaPQ)AAI3626838
035 $a AAI3626838
040 $a MiAaPQ $c MiAaPQ
100 1 $a Lin, Tsung-Han. $3 708675
245 1 0 $a Stable and Efficient Sparse Recovery for Machine Learning and Wireless Communication.
300 $a 132 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-10(E), Section: B.
500 $a Adviser: H. T. Kung.
502 $a Thesis (Ph.D.)--Harvard University, 2014.
506 $a This item must not be sold to any third party vendors.
520 $a Recent theoretical study shows that the sparsest solution to an underdetermined linear system is unique, provided the solution vector is sufficiently sparse, and the operator matrix has sufficiently incoherent column vectors. In addition, efficient algorithms have been discovered to find such solutions. This intriguing result opens a new door for many potential applications. In this thesis, we study the design of a class of greedy algorithms that are extremely efficient, e.g., Orthogonal Matching Pursuit (OMP). These greedy algorithms suffer from a stability issue that the greedy selection approach always make locally optimal decisions, thereby easily biasing and mistaking the solutions in particular under data noise. We propose a solution approach that in designing greedy algorithms, new constraints can be devised by leveraging application-specific insights and incorporated into the algorithms. Given that sparse recovery problems by definition are underdetermined, introducing additional constraints can significantly improve the stability of greedy algorithms, yet retain their efficiency.
520 $a We demonstrate the effectiveness of the proposed solution approach in two example applications: image classification with semi-supervised machine learning, and medium access control in multiuser MIMO networks. In image classification, we show that by introducing a nonnegativity constraint in both feature dictionary learning and feature extraction, we are able to obtain effective feature-space representations for classification purposes, especially when labeled training samples are limited. Our solution approach outperforms the classical OMP approach in classification accuracy, and is competitive with other best-known methods, while requiring much less computation. In multiuser MIMO networks, we show that sparse recovery allows us to identify transmitting host stations and estimate channel statistics from overlapping symbol sequences. The receive antenna diversity on a base station leads to a "same-support" constraint that the received signals share a same set of source transmitters. This constraint can significantly improve the convergence speed of the recovery algorithm. Moreover, this new way of concurrent channel estimation has implications on medium access strategy in multiuser MIMO for delivering throughput scalable to the available number of antennas installed on a base station.
590 $a School code: 0084.
650 4 $a Computer science. $3 199325
690 $a 0984
710 2 $a Harvard University. $b Engineering and Applied Sciences. $3 708676
773 0 $t Dissertation Abstracts International $g 75-10B(E).
790 $a 0084
791 $a Ph.D.
792 $a 2014
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3626838