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

Overparameterization and Double Desc...

Luzi, Lorenzo,

Linked to FindBook

Google Book

Amazon

博客來

Overparameterization and Double Descent in PCA, GANs, and Diffusion Models /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Overparameterization and Double Descent in PCA, GANs, and Diffusion Models // Lorenzo Luzi.
Author:	Luzi, Lorenzo,
Description:	1 electronic resource (179 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
Contained By:	Dissertations Abstracts International86-02B.
Subject:	Mechanics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31532842
ISBN:	9798383416969

Overparameterization and Double Descent in PCA, GANs, and Diffusion Models /
Luzi, Lorenzo,

Overparameterization and Double Descent in PCA, GANs, and Diffusion Models /Lorenzo Luzi. - 1 electronic resource (179 pages)

Source: Dissertations Abstracts International, Volume: 86-02, Section: B.

This PhD thesis constitutes a synthesis of my doctoral work, which addresses various aspects of study related to generative modeling with a particular focus on overparameterization. Using a novel method we call pseudo-supervision, we investigate approaches toward characterization of overparameterization behaviors, including double descent, of GANs as well as PCA-like problems. Extending pseudo-supervision to diffusion models, we see that it can be used to create an inductive bias; we demonstrate that this allows us to train our model with lower generalization error and faster convergence time compared to the baseline. I additionally introduce a novel method called Boomerang to extend our study of diffusion models, showing that they can be used for local sampling in image manifolds. Finally, in an approach we titled WaM, I extend FID to include non-Gaussian distributions by using a Gaussian mixture model and a bound on the 2-Wasserstein metric for Gaussian mixture models to define a metric on non-Gaussian features.

English

ISBN: 9798383416969Subjects--Topical Terms:

525881
Mechanics.
Subjects--Index Terms:

Overparameterization

Overparameterization and Double Descent in PCA, GANs, and Diffusion Models /
LDR:02545nmm a22004573i 4500 001 2431634
005 20250616055544.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798383416969
035 $a (MiAaPQD)AAI31532842
035 $a (MiAaPQD)0187rice5171Luzi
035 $a AAI31532842
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Luzi, Lorenzo, $e author. $3 3820540
245 1 0 $a Overparameterization and Double Descent in PCA, GANs, and Diffusion Models / $c Lorenzo Luzi.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (179 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: 86-02, Section: B.
500 $a Advisors: Baraniuk, Richard G. Committee members: Allen, Genevera; Kyrillidis, Anastasios.
502 $b Ph.D. $c Rice University $d 2024.
520 $a This PhD thesis constitutes a synthesis of my doctoral work, which addresses various aspects of study related to generative modeling with a particular focus on overparameterization. Using a novel method we call pseudo-supervision, we investigate approaches toward characterization of overparameterization behaviors, including double descent, of GANs as well as PCA-like problems. Extending pseudo-supervision to diffusion models, we see that it can be used to create an inductive bias; we demonstrate that this allows us to train our model with lower generalization error and faster convergence time compared to the baseline. I additionally introduce a novel method called Boomerang to extend our study of diffusion models, showing that they can be used for local sampling in image manifolds. Finally, in an approach we titled WaM, I extend FID to include non-Gaussian distributions by using a Gaussian mixture model and a bound on the 2-Wasserstein metric for Gaussian mixture models to define a metric on non-Gaussian features.
546 $a English
590 $a School code: 0187
650 4 $a Mechanics. $3 525881
650 4 $a Electrical engineering. $3 649834
650 4 $a Computer engineering. $3 621879
650 4 $a Medical imaging. $3 3172799
653 $a Overparameterization
653 $a Generative models
653 $a Generative adversarial networks
653 $a Diffusion models
653 $a Double descent
690 $a 0544
690 $a 0346
690 $a 0464
690 $a 0574
710 2 $a Rice University. $b Electrical and Computer Engineering. $e degree granting institution. $3 3820541
720 1 $a Baraniuk, Richard G. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-02B.
790 $a 0187
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31532842