國立虎尾科技大學 |

Advancing Generative Models for Real-World Applications.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Advancing Generative Models for Real-World Applications./
Author:	Choi, Eun Young.
Description:	1 online resource (223 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-08, Section: B.
Contained By:	Dissertations Abstracts International85-08B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798381450255

Advancing Generative Models for Real-World Applications.
Choi, Eun Young.

Advancing Generative Models for Real-World Applications. - 1 online resource (223 pages)

Source: Dissertations Abstracts International, Volume: 85-08, Section: B.

Thesis (Ph.D.)--Stanford University, 2023.

Includes bibliographical references

While generative models hold thrilling potential, their limited usability presents substantial challenges for their widespread adoption in real-world applications. Specifically, existing methods tend to amplify harmful societal biases ingrained in their training data and often fail to accurately reflect subjective user specifications such as style in the generated outputs. Furthermore, a notable performance gap exists when handling data distributions with unique structures, such as periodicity, restricting their applicability beyond image and text data. This dissertation considers all such facets to help construct safe, reliable generative AI systems for practical integration and deployment.First, we present a methodological framework for tackling the challenges of bias mitigation and controllability. Building on the classical approach of density ratio estimation (DRE), we develop techniques to correct a learned model distribution such that it exhibits characteristics that are more closely aligned with an alternative target distribution of interest. Together, these contributions not only yield a new theoretical framework for DRE, but also improve performance on a diverse set of downstream tasks such as domain adaptation, data augmentation, and mutual information estimation. Next, we present two real-world applications of these methods for societal applications. We demonstrate that: (a) our reweighted generative modeling framework successfully mitigates dataset bias, and (b) more controllable models can better customize AI-generated music to individual preferences and assist the creative process. Finally, we conclude by developing new learning algorithms that incorporate domain-specific inductive biases into generative models for wireless communications, as well as for discrete data distributions.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381450255Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Advancing Generative Models for Real-World Applications.
LDR:03039ntm a22003257 4500 001 1146415
005 20240812064610.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381450255
035 $a (MiAaPQ)AAI30765844
035 $a (MiAaPQ)STANFORDky644hz0016
035 $a AAI30765844
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Choi, Eun Young. $3 1471802
245 1 0 $a Advancing Generative Models for Real-World Applications.
264 0 $c 2023
300 $a 1 online resource (223 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: 85-08, Section: B.
500 $a Advisor: Ermon, Stefano;Koyejo, Sanmi;Re, Chris.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
504 $a Includes bibliographical references
520 $a While generative models hold thrilling potential, their limited usability presents substantial challenges for their widespread adoption in real-world applications. Specifically, existing methods tend to amplify harmful societal biases ingrained in their training data and often fail to accurately reflect subjective user specifications such as style in the generated outputs. Furthermore, a notable performance gap exists when handling data distributions with unique structures, such as periodicity, restricting their applicability beyond image and text data. This dissertation considers all such facets to help construct safe, reliable generative AI systems for practical integration and deployment.First, we present a methodological framework for tackling the challenges of bias mitigation and controllability. Building on the classical approach of density ratio estimation (DRE), we develop techniques to correct a learned model distribution such that it exhibits characteristics that are more closely aligned with an alternative target distribution of interest. Together, these contributions not only yield a new theoretical framework for DRE, but also improve performance on a diverse set of downstream tasks such as domain adaptation, data augmentation, and mutual information estimation. Next, we present two real-world applications of these methods for societal applications. We demonstrate that: (a) our reweighted generative modeling framework successfully mitigates dataset bias, and (b) more controllable models can better customize AI-generated music to individual preferences and assist the creative process. Finally, we conclude by developing new learning algorithms that incorporate domain-specific inductive biases into generative models for wireless communications, as well as for discrete data distributions.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Stanford University. $3 1184533
773 0 $t Dissertations Abstracts International $g 85-08B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30765844 $z click for full text (PQDT)