東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Convex relaxation for low-dimensiona...

Oymak, Samet.

FindBook

Google Book

Amazon

博客來

Convex relaxation for low-dimensional representation: Phase transitions and limitations.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Convex relaxation for low-dimensional representation: Phase transitions and limitations./
作者:	Oymak, Samet.
面頁冊數:	302 p.
附註:	Source: Dissertation Abstracts International, Volume: 76-02(E), Section: B.
Contained By:	Dissertation Abstracts International76-02B(E).
標題:	Engineering, Electronics and Electrical. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3636897
ISBN:	9781321188936

Convex relaxation for low-dimensional representation: Phase transitions and limitations.
Oymak, Samet.

Convex relaxation for low-dimensional representation: Phase transitions and limitations. - 302 p.

Source: Dissertation Abstracts International, Volume: 76-02(E), Section: B.

Thesis (Ph.D.)--California Institute of Technology, 2015.

There is a growing interest in taking advantage of possible patterns and structures in data so as to extract the desired information and overcome the curse of dimensionality. In a wide range of applications, including computer vision, machine learning, medical imaging, and social networks, the signal that gives rise to the observations can be modeled to be approximately sparse and exploiting this fact can be very beneficial. This has led to an immense interest in the problem of efficiently reconstructing a sparse signal from limited linear observations. More recently, low-rank approximation techniques have become prominent tools to approach problems arising in machine learning, system identification and quantum tomography.

ISBN: 9781321188936Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

Convex relaxation for low-dimensional representation: Phase transitions and limitations.
LDR:03522nmm a2200313 4500 001 2055715
005 20150217125041.5
008 170521s2015 ||||||||||||||||| ||eng d
020 $a 9781321188936
035 $a (MiAaPQ)AAI3636897
035 $a AAI3636897
040 $a MiAaPQ $c MiAaPQ
100 1 $a Oymak, Samet. $3 3169403
245 1 0 $a Convex relaxation for low-dimensional representation: Phase transitions and limitations.
300 $a 302 p.
500 $a Source: Dissertation Abstracts International, Volume: 76-02(E), Section: B.
500 $a Adviser: Babak Hassibi.
502 $a Thesis (Ph.D.)--California Institute of Technology, 2015.
520 $a There is a growing interest in taking advantage of possible patterns and structures in data so as to extract the desired information and overcome the curse of dimensionality. In a wide range of applications, including computer vision, machine learning, medical imaging, and social networks, the signal that gives rise to the observations can be modeled to be approximately sparse and exploiting this fact can be very beneficial. This has led to an immense interest in the problem of efficiently reconstructing a sparse signal from limited linear observations. More recently, low-rank approximation techniques have become prominent tools to approach problems arising in machine learning, system identification and quantum tomography.
520 $a In sparse and low-rank estimation problems, the challenge is the inherent intractability of the objective function, and one needs efficient methods to capture the low-dimensionality of these models. Convex optimization is often a promising tool to attack such problems. An intractable problem with a combinatorial objective can often be "relaxed" to obtain a tractable but almost as powerful convex optimization problem. This dissertation studies convex optimization techniques that can take advantage of low-dimensional representations of the underlying high-dimensional data. We provide provable guarantees that ensure that the proposed algorithms will succeed under reasonable conditions, and answer questions of the following flavor: 1. For a given number of measurements, can we reliably estimate the true signal? 2. If so, how good is the reconstruction as a function of the model parameters?
520 $a More specifically, i) Focusing on linear inverse problems, we generalize the classical error bounds known for the least-squares technique to the lasso formulation, which incorporates the signal model. ii) We show that intuitive convex approaches do not perform as well as expected when it comes to signals that have multiple low-dimensional structures simultaneously. iii) Finally, we propose convex relaxations for the graph clustering problem and give sharp performance guarantees for a family of graphs arising from the so-called stochastic block model. We pay particular attention to the following aspects. For i) and ii), we aim to provide a general geometric framework, in which the results on sparse and low-rank estimation can be obtained as special cases. For i) and iii), we investigate the precise performance characterization, which yields the right constants in our bounds and the true dependence between the problem parameters.
590 $a School code: 0037.
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Applied Mathematics. $3 1669109
650 4 $a Computer Science. $3 626642
690 $a 0544
690 $a 0364
690 $a 0984
710 2 $a California Institute of Technology. $b Electrical Engineering. $3 2093069
773 0 $t Dissertation Abstracts International $g 76-02B(E).
790 $a 0037
791 $a Ph.D.
792 $a 2015
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3636897