MARC보기
LDR02414nam u200421 4500
001000000422854
00520190215170449
008181129s2017 |||||||||||||||||c||eng d
020 ▼a 9780438373914
035 ▼a (MiAaPQ)AAI10608668
035 ▼a (MiAaPQ)wisc:14701
040 ▼a MiAaPQ ▼c MiAaPQ ▼d 247004
0820 ▼a 310
1001 ▼a Zhang, Luwan.
24510 ▼a Topics on Euclidean Distance Matrix and Unsupervised Ensemble Learning.
260 ▼a [S.l.]: ▼b The University of Wisconsin - Madison., ▼c 2017.
260 1 ▼a Ann Arbor: ▼b ProQuest Dissertations & Theses, ▼c 2017.
300 ▼a 103 p.
500 ▼a Source: Dissertation Abstracts International, Volume: 80-01(E), Section: B.
500 ▼a Adviser: Ming Yuan.
5021 ▼a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2017.
520 ▼a This thesis is devoted to the study of Euclidean distance matrix and unsupervised ensemble learning under the high-dimensional setting. It consists of three pieces of work, focusing on proposing a shrinkage estimator of Euclidean distance matrix
520 ▼a In the first part of thesis, we discuss the problem of recovering an Euclidean distance matrix from noisy or imperfect observations of pairwise dissimilarity scores between a set of objects. This problem naturally arises in many different contex
520 ▼a As a sequel of Chapter 1, the second part pays attention to conducting statistical analyses after mapping a set of objects from an arbitrary domain to the Euclidean space. In this chapter, we specifically consider the generalization of ANOVA mod
520 ▼a The third part mainly concerns developing a new ensemble method for classification problems when the true class labels are not available (a.k.a unsupervised setting). The motivation arises from an intrinsic drawback of crowdsourcing, in which an
520 ▼a Finally, we conclude the thesis in Chapter 4.
590 ▼a School code: 0262.
650 4 ▼a Statistics.
690 ▼a 0463
71020 ▼a The University of Wisconsin - Madison. ▼b Statistics.
7730 ▼t Dissertation Abstracts International ▼g 80-01B(E).
773 ▼t Dissertation Abstract International
790 ▼a 0262
791 ▼a Ph.D.
792 ▼a 2017
793 ▼a English
85640 ▼u http://www.riss.kr/pdu/ddodLink.do?id=T14996627 ▼n KERIS ▼z 이 자료의 원문은 한국교육학술정보원에서 제공합니다.
980 ▼a 201812 ▼f 2019
990 ▼a ***1012033