MARC보기
LDR02261nmm uu200409 4500
001000000333258
00520240805172707
008181129s2018 |||||||||||||||||c||eng d
020 ▼a 9780438324534
035 ▼a (MiAaPQ)AAI10815317
035 ▼a (MiAaPQ)berkeley:17802
040 ▼a MiAaPQ ▼c MiAaPQ ▼d 248032
0820 ▼a 310
1001 ▼a Saha, Sujayam.
24510 ▼a Information Theory, Dimension Reduction and Density Estimation.
260 ▼a [S.l.] : ▼b University of California, Berkeley., ▼c 2018
260 1 ▼a Ann Arbor : ▼b ProQuest Dissertations & Theses, ▼c 2018
300 ▼a 160 p.
500 ▼a Source: Dissertation Abstracts International, Volume: 80-01(E), Section: B.
500 ▼a Advisers: Bin Yu
5021 ▼a Thesis (Ph.D.)--University of California, Berkeley, 2018.
520 ▼a This thesis documents three different contributions in statistical learning theory. They were developed with careful emphasis on addressing the demands of modern statistical analysis upon large-scale modern datasets. The contributions concern th
520 ▼a In Chapter 2, I describe the development of an unifying treatment of the study of inequalities between f-divergences, which are a general class of divergences between probability measures which include as special cases many commonly used diverge
520 ▼a In Chapter 3, I describe the development of a new dimension reduction technique specially suited for interpretable inference in supervised learning problems involving large-dimensional data. This new technique, Supervised Random Projections (SRP
520 ▼a In Chapter 4, I describe the development of several adaptivity properties of the Non-Parametric Maximum Likelihood Estimator (NPMLE) in the problem of estimating an unknown gaussian location mixture density based on independent identically distr
590 ▼a School code: 0028.
650 4 ▼a Statistics.
690 ▼a 0463
71020 ▼a University of California, Berkeley. ▼b Statistics.
7730 ▼t Dissertation Abstracts International ▼g 80-01B(E).
773 ▼t Dissertation Abstract International
790 ▼a 0028
791 ▼a Ph.D.
792 ▼a 2018
793 ▼a English
85640 ▼u http://www.riss.kr/pdu/ddodLink.do?id=T14998167 ▼n KERIS
980 ▼a 201812 ▼f 2019
990 ▼a 관리자