MARC보기
LDR00000nmm u2200205 4500
001000000330360
00520241029143712
008181129s2018 ||| | | | eng d
020 ▼a 9780438353886
035 ▼a (MiAaPQ)AAI10843849
035 ▼a (MiAaPQ)umn:19501
040 ▼a MiAaPQ ▼c MiAaPQ ▼d 248032
0491 ▼f DP
0820 ▼a 621.3
1001 ▼a Li, Xingguo.
24510 ▼a Structured Learning with Parsimony in Measurements and Computations: Theory, Algorithms, and Applications.
260 ▼a [S.l.] : ▼b University of Minnesota., ▼c 2018
260 1 ▼a Ann Arbor : ▼b ProQuest Dissertations & Theses, ▼c 2018
300 ▼a 309 p.
500 ▼a Source: Dissertation Abstracts International, Volume: 80-01(E), Section: B.
500 ▼a Adviser: Jarvis D. Haupt.
5021 ▼a Thesis (Ph.D.)--University of Minnesota, 2018.
520 ▼a In modern "Big Data" applications, structured learning is the most widely employed methodology. Within this paradigm, the fundamental challenge lies in developing practical, effective algorithmic inference methods. Often (e.g., deep learning) su
520 ▼a Toward this end, we make efforts to investigate the theoretical properties of models and algorithms that present significant improvement in measurement and computation requirement. In particular, we first develop randomized approaches for dimens
590 ▼a School code: 0130.
650 4 ▼a Electrical engineering.
650 4 ▼a Computer engineering.
650 4 ▼a Computer science.
690 ▼a 0544
690 ▼a 0464
690 ▼a 0984
71020 ▼a University of Minnesota. ▼b Electrical Engineering.
7730 ▼t Dissertation Abstracts International ▼g 80-01B(E).
773 ▼t Dissertation Abstract International
790 ▼a 0130
791 ▼a Ph.D.
792 ▼a 2018
793 ▼a English
85640 ▼u http://www.riss.kr/pdu/ddodLink.do?id=T14999952 ▼n KERIS
980 ▼a 201812 ▼f 2019
990 ▼a 관리자 ▼b 관리자