語系:
繁體中文
English
說明(常見問題)
回圖書館首頁
手機版館藏查詢
登入
回首頁
到查詢結果
[ null ]
切換:
標籤
|
MARC模式
|
ISBD
Principled Algorithms for Domain Ada...
~
Chen, Yining,
FindBook
Google Book
Amazon
博客來
Principled Algorithms for Domain Adaptation and Generalization /
紀錄類型:
書目-電子資源 : Monograph/item
正題名/作者:
Principled Algorithms for Domain Adaptation and Generalization // Yining Chen.
作者:
Chen, Yining,
面頁冊數:
1 electronic resource (229 pages)
附註:
Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:
Dissertations Abstracts International85-04B.
標題:
Active learning. -
電子資源:
https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615214
ISBN:
9798380485050
Principled Algorithms for Domain Adaptation and Generalization /
Chen, Yining,
Principled Algorithms for Domain Adaptation and Generalization /
Yining Chen. - 1 electronic resource (229 pages)
Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Machine learning models are increasingly applied to datasets different from the training datasets. The performance of models often degrades when tested on unseen scenarios. Empirically, many algorithms have been used for domain adaptation and generalization, but few methods have been able to surpass empirical risk minimization consistently on common benchmarks. Theoretically, traditional learning theory offers limited insights for distributional shift problems. The main goal of this thesis is to bridge the gap between the theory and practice for domain shift problems, and to develop principled algorithms that have better robustness guarantees.We study three domain shift problems with increased supervised from the target domain. We first study domain generalization where no target data is available during training. We show that feature-matching algorithms generalize better when the distinguishing property of the signal feature is indeed conditional distributional invariance. Next, we study domain adaptation where unlabeled target data is available. We show that self-training helps when the target is more diverse than the source. Lastly, we study active online learning under domain shift. We show that uncertainty sampling leads to better query-regret tradeoff when there is hidden domain structure. In all three problems, the synergy of explicit bias from the algorithm and implicit bias from the domain shift structure contributes to successful transfer between domains.
English
ISBN: 9798380485050Subjects--Topical Terms:
527777
Active learning.
Principled Algorithms for Domain Adaptation and Generalization /
LDR
:02767nmm a22003733i 4500
001
2400457
005
20250522084130.5
006
m o d
007
cr|nu||||||||
008
251215s2023 miu||||||m |||||||eng d
020
$a
9798380485050
035
$a
(MiAaPQD)AAI30615214
035
$a
(MiAaPQD)STANFORDdm107nr6713
035
$a
AAI30615214
040
$a
MiAaPQD
$b
eng
$c
MiAaPQD
$e
rda
100
1
$a
Chen, Yining,
$e
author.
$3
3770456
245
1 0
$a
Principled Algorithms for Domain Adaptation and Generalization /
$c
Yining Chen.
264
1
$a
Ann Arbor :
$b
ProQuest Dissertations & Theses,
$c
2023
300
$a
1 electronic resource (229 pages)
336
$a
text
$b
txt
$2
rdacontent
337
$a
computer
$b
c
$2
rdamedia
338
$a
online resource
$b
cr
$2
rdacarrier
500
$a
Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
500
$a
Advisors: Ma, Tengyu Committee members: Ermon, Stefano; Hashimoto, Tatsunori; Bent, Stacey F.
502
$b
Ph.D.
$c
Stanford University
$d
2023.
520
$a
Machine learning models are increasingly applied to datasets different from the training datasets. The performance of models often degrades when tested on unseen scenarios. Empirically, many algorithms have been used for domain adaptation and generalization, but few methods have been able to surpass empirical risk minimization consistently on common benchmarks. Theoretically, traditional learning theory offers limited insights for distributional shift problems. The main goal of this thesis is to bridge the gap between the theory and practice for domain shift problems, and to develop principled algorithms that have better robustness guarantees.We study three domain shift problems with increased supervised from the target domain. We first study domain generalization where no target data is available during training. We show that feature-matching algorithms generalize better when the distinguishing property of the signal feature is indeed conditional distributional invariance. Next, we study domain adaptation where unlabeled target data is available. We show that self-training helps when the target is more diverse than the source. Lastly, we study active online learning under domain shift. We show that uncertainty sampling leads to better query-regret tradeoff when there is hidden domain structure. In all three problems, the synergy of explicit bias from the algorithm and implicit bias from the domain shift structure contributes to successful transfer between domains.
546
$a
English
590
$a
School code: 0212
650
4
$a
Active learning.
$3
527777
650
4
$a
Computer science.
$3
523869
690
$a
0800
690
$a
0984
710
2
$a
Stanford University.
$e
degree granting institution.
$3
3765820
720
1
$a
Ma, Tengyu
$e
degree supervisor.
773
0
$t
Dissertations Abstracts International
$g
85-04B.
790
$a
0212
791
$a
Ph.D.
792
$a
2023
856
4 0
$u
https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615214
筆 0 讀者評論
館藏地:
全部
電子資源
出版年:
卷號:
館藏
1 筆 • 頁數 1 •
1
條碼號
典藏地名稱
館藏流通類別
資料類型
索書號
使用類型
借閱狀態
預約狀態
備註欄
附件
W9508777
電子資源
11.線上閱覽_V
電子書
EB
一般使用(Normal)
在架
0
1 筆 • 頁數 1 •
1
多媒體
評論
新增評論
分享你的心得
Export
取書館
處理中
...
變更密碼
登入
(1)帳號:一般為「身分證號」;外籍生或交換生則為「學號」。 (2)密碼:預設為帳號末四碼。
帳號
.
密碼
.
請在此電腦上記得個人資料
取消
忘記密碼? (請注意!您必須已在系統登記E-mail信箱方能使用。)