東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Principled Algorithms for Domain Ada...

Chen, Yining,

Linked to FindBook

Google Book

Amazon

博客來

Principled Algorithms for Domain Adaptation and Generalization /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Principled Algorithms for Domain Adaptation and Generalization // Yining Chen.
Author:	Chen, Yining,
Description:	1 electronic resource (229 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:	Dissertations Abstracts International85-04B.
Subject:	Active learning. -
Online resource:	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