MARC보기
LDR01651nmm uu200385 4500
001000000333838
00520240805174631
008181129s2018 |||||||||||||||||c||eng d
020 ▼a 9780438049475
035 ▼a (MiAaPQ)AAI10823658
035 ▼a (MiAaPQ)princeton:12599
040 ▼a MiAaPQ ▼c MiAaPQ ▼d 248032
0820 ▼a 519
1001 ▼a Wang, Yao.
24510 ▼a Estimation Error for Regression and Optimal Convergence Rate.
260 ▼a [S.l.] : ▼b Princeton University., ▼c 2018
260 1 ▼a Ann Arbor : ▼b ProQuest Dissertations & Theses, ▼c 2018
300 ▼a 62 p.
500 ▼a Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
500 ▼a Adviser: Weinan E.
5021 ▼a Thesis (Ph.D.)--Princeton University, 2018.
520 ▼a In this thesis, we study the optimal convergence rate for the universal estimation error. Let F be the excess loss class associated with the hypothesis space and n be the size of the data set, we prove that if the Fat-shattering dimension satisf
520 ▼a Training in practice may only explore a certain subspace in F. It is useful to bound the complexity of the subspace explored instead of the whole F. This is done for the gradient descent method.
590 ▼a School code: 0181.
650 4 ▼a Applied mathematics.
690 ▼a 0364
71020 ▼a Princeton University. ▼b Mathematics.
7730 ▼t Dissertation Abstracts International ▼g 79-10B(E).
773 ▼t Dissertation Abstract International
790 ▼a 0181
791 ▼a Ph.D.
792 ▼a 2018
793 ▼a English
85640 ▼u http://www.riss.kr/pdu/ddodLink.do?id=T14998591 ▼n KERIS
980 ▼a 201812 ▼f 2019
990 ▼a 관리자