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

Theoretical foundations and algorith...

Rostamizadeh, Afshin.

FindBook

Google Book

Amazon

博客來

Theoretical foundations and algorithms for learning with multiple kernels.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Theoretical foundations and algorithms for learning with multiple kernels./
作者:	Rostamizadeh, Afshin.
面頁冊數:	144 p.
附註:	Source: Dissertation Abstracts International, Volume: 71-07, Section: B, page: 4355.
Contained By:	Dissertation Abstracts International71-07B.
標題:	Artificial Intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3408306
ISBN:	9781124043388

Theoretical foundations and algorithms for learning with multiple kernels.
Rostamizadeh, Afshin.

Theoretical foundations and algorithms for learning with multiple kernels. - 144 p.

Source: Dissertation Abstracts International, Volume: 71-07, Section: B, page: 4355.

Thesis (Ph.D.)--New York University, 2010.

Kernel-based algorithms have been used with great success in a variety of machine learning applications. These include algorithms such as support vector machines for classification, kernel ridge regression, ranking algorithms, clustering algorithms, and virtually all popular dimensionality reduction algorithms.

ISBN: 9781124043388Subjects--Topical Terms:

769149
Artificial Intelligence.

Theoretical foundations and algorithms for learning with multiple kernels.
LDR:03431nam 2200373 4500 001 1399850
005 20110930095848.5
008 130515s2010 ||||||||||||||||| ||eng d
020 $a 9781124043388
035 $a (UMI)AAI3408306
035 $a AAI3408306
040 $a UMI $c UMI
100 1 $a Rostamizadeh, Afshin. $3 1678863
245 1 0 $a Theoretical foundations and algorithms for learning with multiple kernels.
300 $a 144 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-07, Section: B, page: 4355.
500 $a Adviser: Mehryar Mohri.
502 $a Thesis (Ph.D.)--New York University, 2010.
520 $a Kernel-based algorithms have been used with great success in a variety of machine learning applications. These include algorithms such as support vector machines for classification, kernel ridge regression, ranking algorithms, clustering algorithms, and virtually all popular dimensionality reduction algorithms.
520 $a But, the choice of the kernel, which is crucial to the success of these algorithms, has been traditionally left entirely to the user. Rather than requesting the user to commit to a specific kernel, multiple kernel algorithms require the user only to specify a family of kernels. This family of kernels can be used by a learning algorithm to form a combined kernel and derive an accurate predictor. This is a problem that has attracted a lot of attention recently, both from the theoretical point of view and from the algorithmic, optimization, and application point of view. This thesis presents a number of novel theoretical and algorithmic results for learning with multiple kernels.
520 $a It gives the first tight margin-based generalization bounds for learning kernels with Lp regularization. In particular, our margin bounds for L1 regularization are shown to have only a logarithmic dependency on the number of kernels, which is a significant improvement over all previous analyses. Our results also include stability-based guarantees for a class of regression algorithms. In all cases, these guarantees indicate the benefits of learning with a large number of kernels.
520 $a We also present a family of new two-stage algorithms for learning kernels based on a notion of alignment and give an extensive analysis of the properties of these algorithms. We show the existence of good predictors for the notion of alignment we define and give efficient algorithms for learning a maximum alignment kernel by showing that the problem can be reduced to a simple quadratic program.
520 $a Finally, we report the results of extensive experiments with our two-stage algorithms, which show an improvement both over the uniform combination of kernels and over other state-of-the-art learning kernel methods for L1 and L2 regularization. These might constitute the first series of results for learning with multiple kernels that demonstrate a consistent improvement over a uniform combination of kernels.
590 $a School code: 0146.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Computer Science. $3 626642
690 $a 0800
690 $a 0984
710 2 $a New York University. $b Computer Science. $3 1065424
773 0 $t Dissertation Abstracts International $g 71-07B.
790 1 0 $a Mohri, Mehryar, $e advisor
790 1 0 $a Cortes, Corinna $e committee member
790 1 0 $a Khot, Subhash $e committee member
790 1 0 $a Spencer, Joel $e committee member
790 1 0 $a Mansour, Yishay $e committee member
790 $a 0146
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3408306